Introduc on to AI

AI is one of the fascina ng and universal fields of Computer science which has a great scope in future. AI holds
a tendency to cause a machine to work as a human.
one of the booming technologies of computer science is Ar ficial Intelligence which is ready to create a new
revolu on in the world by making intelligent machines. The Ar ficial Intelligence is now all around us. It is
currently working with a variety of subfields, ranging from general to specific, such as self-driving cars, playing
chess, proving theorems, playing music, Pain ng, etc.
Ar ficial Intelligence is composed of two words Ar ficial and Intelligence, where Ar ficial defines "man-
made," and intelligence defines "thinking power", hence AI means "a man-made thinking power."
So, we can define AI as:
"It is a branch of computer science by which we can create intelligent machines which can behave like a
human, think like humans, and able to make decisions."
With Ar ficial Intelligence you do not need to preprogram a machine to do some work, despite that you can
create a machine with programmed algorithms which can work with own intelligence, and that is the
awesomeness of AI.

Why Ar ficial Intelligence?

o With the help of AI, you can create such so ware or devices which can solve real-world problems very
easily and with accuracy such as health issues, marke ng, traffic issues, etc.
o With the help of AI, you can create your personal virtual Assistant, such as Cortana, Google Assistant,
Siri, etc.
o With the help of AI, you can build such Robots which can work in an environment where survival of
humans can be at risk.

Goals of Ar ficial Intelligence

Following are the main goals of Ar ficial Intelligence:

1. Replicate human intelligence
2. Solve Knowledge-intensive tasks
 3. An intelligent connec on of percep on and ac on
4. Building a machine which can perform tasks that requires human intelligence such as:
o Proving a theorem
o Playing chess
o Plan some surgical opera on
o Driving a car in traffic
5. Crea ng some system which can exhibit intelligent behavior, learn new things by itself, demonstrate,
explain, and can advise to its user.

What Comprises to Ar ficial Intelligence?

The Intelligence is an intangible part of our brain which is a combina on of Reasoning, learning, problem-solving
percep on, language understanding, etc.

Types of Ar ficial Intelligence

Ar ficial Intelligence can be categorized in several ways, primarily based on two main criteria: capabili es and
func onality.

AI Type 1: Based on Capabili es

1. Weak AI or Narrow AI: Narrow AI, also known as Weak AI, is like a specialist in the world of Ar ficial Intelligence.
Imagine it as a virtual expert dedicated to performing one specific task with intelligence. For example, think of
Apple's Siri. It's pre y smart when it comes to voice commands and answering ques ons, but it doesn't
understand or do much beyond that. Narrow AI operates within strict limits, and if you ask it to step outside its
comfort zone, it might not perform as expected. This type of AI is everywhere in today's world, from self-driving
cars to image recogni on on your smartphone. IBM's Watson is another example of Narrow AI. It's a
supercomputer that combines Expert Systems, Machine Learning, and Natural Language Processing, but it's s ll
a specialist. It's excellent at crunching data and providing insights but doesn't venture far beyond its defined
tasks.

2. General AI: General AI, o en referred to as Strong AI, is like the holy grail of ar ficial intelligence. Picture it as a
system that could do any intellectual task with the efficiency of a human. General AI aims to create machines
that think and learn like humans, but here's the catch: there's no such system in existence yet. Researchers
worldwide are working diligently to make it a reality, but it's a complex journey that will require significant me
and effort.

3. Super AI: Super AI takes AI to another level en rely. It's the pinnacle of machine intelligence, where machines
surpass human capabili es in every cogni ve aspect. These machines can think, reason, solve puzzles, make
 judgments, plan, learn, and communicate independently. However, it's important to note that Super AI is
currently a hypothe cal concept. Achieving such a level of ar ficial intelligence would be nothing short of
revolu onary, and it's a challenge that's s ll on the horizon.

AI Type 2: Based on Func onality

1. Reac ve Machines: Reac ve Machines represent the most basic form of Ar ficial Intelligence. These machines
live in the present moment and don't have memories or past experiences to guide their ac ons. They focus
solely on the current scenario and respond with the best possible ac on based on their programming. An
example of a reac ve machine is IBM's Deep Blue, the chess-playing computer, and Google's AlphaGo, which
excels at the ancient game of Go.

2. Limited Memory: Limited Memory machines can remember some past experiences or data but only for a short
period. They use this stored informa on to make decisions and navigate situa ons. A great example of this type
of AI is seen in self-driving cars. These vehicles store recent data like the speed of nearby cars, distances, and
speed limits to safely navigate the road.

3. Theory of Mind: Theory of Mind AI is s ll in the realm of research and development. These AI systems aim to
understand human emo ons and beliefs and engage in social interac ons much like humans. While this type of
AI hasn't fully materialized yet, researchers are making significant strides toward crea ng machines that can
understand and interact with humans on a deeper, more emo onal level.

4. Self-Awareness: Self-Awareness AI is the future fron er of Ar ficial Intelligence. These machines will be
extraordinarily intelligent, possessing their own consciousness, emo ons, and self-awareness. They'll be smarter
than the human mind itself. However, it's crucial to note that Self-Awareness AI remains a hypothe cal concept
and does not yet exist in reality. Achieving this level of AI would be a monumental leap in technology and
understanding.

Advantages of Ar ficial Intelligence

Following are some main advantages of Ar ficial Intelligence:

o High Accuracy with less errors: AI machines or systems are prone to less errors and high accuracy as it takes
decisions as per pre-experience or informa on.

o High-Speed: AI systems can be of very high-speed and fast-decision making, because of that AI systems can beat
a chess champion in the Chess game.

o High reliability: AI machines are highly reliable and can perform the same ac on mul ple mes with high
accuracy.

o Useful for risky areas: AI machines can be helpful in situa ons such as defusing a bomb, exploring the ocean
floor, where to employ a human can be risky.

o Digital Assistant: AI can be very useful to provide digital assistant to the users such as AI technology is currently
used by various E-commerce websites to show the products as per customer requirement.

o Useful as a public u lity: AI can be very useful for public u li es such as a self-driving car which can make our
journey safer and hassle-free, facial recogni on for security purpose, Natural language processing to
communicate with the human in human-language, etc.
 o Enhanced Security: AI can be very helpful in enhancing security, as It can detect and respond to cyber threats in
real me, helping companies protect their data and systems.

o Aid in Research: AI is very helpful in the research field as it assists researchers by processing and analyzing large
datasets, accelera ng discoveries in fields such as astronomy, genomics, and materials science.

Disadvantages of Ar ficial Intelligence

o High Cost: The hardware and so ware requirement of AI is very costly as it requires lots of maintenance to meet
current world requirements.

o Can't think out of the box: Even we are making smarter machines with AI, but s ll they cannot work out of the
box, as the robot will only do that work for which they are trained, or programmed.

o No feelings and emo ons: AI machines can be an outstanding performer, but s ll it does not have the feeling so
it cannot make any kind of emo onal a achment with human, and may some me be harmful for users if the
proper care is not taken.

o Increase dependency on machines: With the increment of technology, people are ge ng more dependent on
devices and hence they are losing their mental capabili es.

o No Original Crea vity: As humans are so crea ve and can imagine some new ideas but s ll AI machines cannot
beat this power of human intelligence and cannot be crea ve and imagina ve.

o Complexity: Making and keeping AI systems can be very complicated and need a lot of knowledge. This
can make it hard for some groups or people to use them.

o Job Concerns: As AI gets be er, it might take away not just basic jobs but also some skilled ones. This
worries people about losing jobs in different fields.

Challenges of AI

Ar ficial Intelligence offers incredible advantages, but it also presents some challenges that need to be addressed:

o Doing the Right Thing: AI should make the right choices, but some mes it doesn't. It can make mistakes
or do things that aren't fair. We need to teach AI to be be er at making good choices.

o Government and AI: Some mes, governments use AI to keep an eye on people. This can be a problem
for our freedom. We need to make sure they use AI in a good way.

o Bias in AI: AI can some mes be a bit unfair, especially when it comes to recognizing people's faces. This
can cause problems, especially for people who aren't like the majority.

o AI and Social Media: What you see on social media is o en decided by AI. But some mes, AI shows
things that aren't true or are kind of mean. We need to make sure AI shows the right stuff.

o Legal and Regulatory Challenges: The rapid evolu on of AI has outpaced the development of
comprehensive laws and regula ons, leading to uncertainty about issues like liability and responsibility.
Applica ons of AI
 Unit-1 Part-1

Scope of AI:

1. Games:

AI for gaming refers to the integra on of ar ficial intelligence techniques

and technologies into video games to create more dynamic, responsive,
and immersive gameplay experiences.

Applica ons of AI in Gaming Industry

There are several ways in which ar ficial intelligence (AI) is being used in
the gaming industry:

1. Non-player characters (NPCs): AI is o en used to control the

behavior of NPCs in games. These characters can interact with
players in a more realis c and dynamic way, adding to the immersion
of the game.

2. Game design: AI is being used to design and balance game levels, as

well as to generate new content such as enemies and items. This
helps developers create more diverse and interes ng games with
less effort.

3. Gameplay: AI can enhance gameplay by providing intelligent

opponents for players to face off against. This makes games more
challenging and rewarding for players.

4. Virtual assistants: Some games include virtual assistants that can

help players by providing informa on or guidance during gameplay.
These assistants use natural language processing (NLP) to
understand and respond to player requests.
 5. Personaliza on: AI can personalize gameplay for individual players
by adap ng to their preferences and playstyle. This helps keep
players engaged and mo vated to con nue playing.

6. Predic ve analy cs: AI can be used to analyze player data and

predict how they will behave in the future. This can help developers
design games that are more engaging and tailored to the
preferences of specific player segments.

7. Fraud detec on: AI can be used to detect fraudulent ac vity in

online games, such as chea ng or hacking. This helps maintain the
integrity of the game and ensures that players have a fair and
enjoyable experience.

Overall, AI is helping to improve the quality and variety of games available,

as well as making them more immersive and engaging for players.

Limita ons of Ar ficial Intelligence in Gaming Industry

There are a few limita ons to the use of ar ficial intelligence (AI) in the
gaming industry:

1. Cost: Developing AI technology can be expensive, which can be a

barrier for smaller studios or indie developers.

2. Complexity: Incorpora ng AI into a game can be complex and

requires specialized knowledge and exper se. This can make it
difficult for developers who are not familiar with AI to implement it
in their games.

3. Limited intelligence: While AI can be very sophis cated, it is s ll

limited by its programming and the data it has been trained on. This
means that AI may not be able to respond appropriately to
unexpected situa ons or player ac ons.
4. Lack of crea vity: AI can generate content and design levels, but it
may not be able to come up with truly crea ve or original ideas. This
can limit the poten al of AI in the gaming industry.

5. Ethical concerns: Some people may have ethical concerns about the
use of AI in games, such as the poten al for AI to be used for
unethical purposes or to perpetuate harmful biases.
Game Playing in Ar ficial Intelligence

Game playing in AI is an ac ve area of research and has many prac cal

applica ons, including game development, educa on, and military
training. By simula ng game playing scenarios, AI algorithms can be used
to develop more effec ve decision-making systems for real-world
applica ons.

Game Playing is an important domain of ar ficial intelligence. Games

don’t require much knowledge; the only knowledge we need to provide is
the rules, legal moves and the condi ons of winning or losing the game.
Both players try to win the game. So, both of them try to make the best
move possible at each turn. Searching techniques like BFS(Breadth First
Search) are not accurate for this as the branching factor is very high, so
searching will take a lot of me. So, we need another search procedures
that improve –

 Generate procedure so that only good moves are generated.

 Test procedure so that the best move can be explored first.

Game playing is a popular applica on of ar ficial intelligence that involves

the development of computer programs to play games, such as chess,
checkers, or Go. The goal of game playing in ar ficial intelligence is to
develop algorithms that can learn how to play games and make decisions
that will lead to winning outcomes.

1. One of the earliest examples of successful game playing AI is the

chess program Deep Blue, developed by IBM, which defeated the
world champion Garry Kasparov in 1997. Since then, AI has been
applied to a wide range of games, including two-player games,
mul player games, and video games.
 2. AlphaGo, developed by DeepMind, was the first machine learning-
based system to defeat a world champion in the game of Go.

There are two main approaches to game playing in AI, rule-based systems
and machine learning-based systems.

1. Rule-based systems use a set of fixed rules to play the game.

2. Machine learning-based systems use algorithms to learn from

experience and make decisions based on that experience.

The most common search technique in game playing is Minimax search

procedure. It is depth-first depth-limited search procedure. It is used for
games like chess and c-tac-toe.

Advantages of Game Playing in Ar ficial Intelligence:

1. Advancement of AI: Game playing has been a driving force behind

the development of ar ficial intelligence and has led to the crea on
of new algorithms and techniques that can be applied to other areas
of AI.

2. Educa on and training: Game playing can be used to teach AI

techniques and algorithms to students and professionals, as well as
to provide training for military and emergency response personnel.

3. Research: Game playing is an ac ve area of research in AI and

provides an opportunity to study and develop new techniques for
decision-making and problem-solving.

4. Real-world applica ons: The techniques and algorithms developed

for game playing can be applied to real-world applica ons, such as
robo cs, autonomous systems, and decision support systems.

Disadvantages of Game Playing in Ar ficial Intelligence:

1. Limited scope: The techniques and algorithms developed for game
playing may not be well-suited for other types of applica ons and
may need to be adapted or modified for different domains.

2. Computa onal cost: Game playing can be computa onally

expensive, especially for complex games such as chess or Go, and
may require powerful computers to achieve real- me performance.
 Adversarial Search

Adversarial search is a search, where we examine the problem which

arises when we

o There might be some situa ons where more than one agent is
searching for the solu on in the same search space, and this
situa on usually occurs in game playing.

o The environment with more than one agent is termed as mul -

agent environment, in which each agent is an opponent of other
agent and playing against each other. Each agent needs to consider
the ac on of other agent and effect of that ac on on their
performance.

o So, Searches in which two or more players with conflic ng goals are
trying to explore the same search space for the solu on, are called
adversarial searches, o en known as Games.

Types of Games in AI:

Determinis c Chance Moves

Perfect Chess, Checkers, go, Backgammon, monopoly

informa on Othello

Imperfect Ba leships, blind, c- Bridge, poker, scrabble,

informa on tac-toe nuclear war
 o Perfect informa on: A game with the perfect informa on is that in
which agents can look into the complete board. Agents have all the
informa on about the game, and they can see each other moves
also. Examples are Chess, Checkers, Go, etc.

o Imperfect informa on: If in a game agents do not have all

informa on about the game and not aware with what's going on,
such type of games are called the game with imperfect informa on,
such as c-tac-toe, Ba leship, blind, Bridge, etc.

o Determinis c games: Determinis c games are those games which

follow a strict pa ern and set of rules for the games, and there is no
randomness associated with them. Examples are chess, Checkers,
Go, c-tac-toe, etc.

o Non-determinis c games: Non-determinis c are those games which

have various unpredictable events and has a factor of chance or luck.
This factor of chance or luck is introduced by either dice or cards.
These are random, and each ac on response is not fixed. Such
games are also called as stochas c games.
Example: Backgammon, Monopoly, Poker, etc.

Note: In this topic, we will discuss determinis c games, fully observable

environment, zero-sum, and where each agent acts alterna vely.

Zero-Sum Game

The phrase "zero-sum game" comes from game theory and the no on
that if one person wins and the other person loses, this produces a net
gain of zero.

o Zero-sum games are adversarial search which involves pure

compe on.
 o In Zero-sum game each agent's gain or loss of u lity is exactly
balanced by the losses or gains of u lity of another agent.

o One player of the game try to maximize one single value, while other
player tries to minimize it.

o Each move by one player in the game is called as ply.

o Chess and c-tac-toe are examples of a Zero-sum game.

Zero-sum game: Embedded thinking

The Zero-sum game involved embedded thinking in which one agent or

player is trying to figure out:

o What to do.

o How to decide the move

o Needs to think about his opponent as well

o The opponent also thinks what to do

Each of the players is trying to find out the response of his opponent to
their ac ons. This requires embedded thinking or backward reasoning to
solve the game problems in AI.

Formaliza on of the problem:

A game can be defined as a type of search in AI which can be formalized

of the following elements:

o Ini al state: It specifies how the game is set up at the start.

o Player(s): It specifies which player has moved in the state space.

o Ac on(s): It returns the set of legal moves in state space.

 o Result(s, a): It is the transi on model, which specifies the result of
moves in the state space.

o Terminal-Test(s): Terminal test is true if the game is over, else it is

false at any case. The state where the game ends is called terminal
states.

o U lity(s, p): A u lity func on gives the final numeric value for a
game that ends in terminal states s for player p. It is also called payoff
func on. For Chess, the outcomes are a win, loss, or draw and its
payoff values are +1, 0, ½. And for c-tac-toe, u lity values are +1, -
1, and 0.

What is Theorem proving?

Theorem Proving: The Basics of Automated Reasoning

Introduction

Theorem proving is an essen al area of research within automated

reasoning, with its ability to prove mathema cal theorems automa cally
being of immense significance in various domains. Essen ally, theorem
proving is a branch of automated reasoning where computers and
algorithms can prove mathema cal theorems automa cally, thereby
making the process faster, more efficient, and less prone to errors than
manual methods.

This field has gained significant trac on with the incredible advancements
in machine learning, cogni ve compu ng, and ar ficial intelligence in the
past few years. Theorem proving is a vital tool in fields such as computer
science, mathema cs, physics, engineering, and ar ficial intelligence.

What is Theorem Proving?

To put it in simple terms, theorem proving is the ability of computers to
prove theorems automa cally using formal logic. It is a sub-discipline of
Automated Reasoning, a branch of ar ficial intelligence whose primary
task is to automa cally prove or disprove mathema cal statements and
proposi ons. Theorem proving has significant advantages over manual
methods of proving a theorem.

In contrast to manual proof methods that involve a complex series of

steps, theorem proving automates the en re process. Automated
reasoning methods are not only faster but also more efficient and require
minimal human interven on. Theorem proving algorithms are based on
formal logic, and they can be used to determine the correctness of logical
statements quickly.

Theorem proving has numerous applica ons. Its applica ons extend to
various fields such as computer science and mathema cs, and it plays an
essen al role in the op miza on of complex systems. In computer
science, theorem proving is commonly used to verify the correctness of
algorithms and so ware systems. In mathema cs, theorem proving helps
Automa ng the tedious process of mathema cal proofs.

Components of Theorem Proving

There are mul ple components to theorem proving. Each component has
a vital role in the overall theorem proving process. These components
include:

Logic: The logic used in theorem proving determines the strength of the
statement or proposi on to be proved. For example, the first-order logic
can handle statements involving natural numbers and sets, while second-
order logic can handle statements involving natural numbers and sets and
second-order statements as well.
Inference Engine: This component is responsible for processing the rules
of inference that are used to create new statements or proposi ons.
Inference engines implement various rules such as Modus Ponens (If A
implies B and A is true, then B is true) and resolu on

Axioms: These are assumed statements or proposi ons that are assumed
to be true and are used to build the theorem. Axioms are the building
blocks of mathema cal theorems, and are assumed to be true or self-
evident.

Lemmas: These are intermediate results that are assumed to be true, and
are essen al in proving the final result.

Advantages of Theorem Proving

Theorem proving is a powerful technology that has many advantages over

tradi onal methods of proof. These benefits include the following:

Automated Process: Theorem proving is an automated process that is

faster and more efficient than manual proof methods.

Op miza on: Theorem proving can help op mize complex systems that
are prone to errors. By iden fying and fixing errors automa cally, theorem
proving helps improve the effec veness and efficiency of these systems.

Correctness: Theorem proving can prove the correctness of a system or

algorithm and uncover errors that may be hard to iden fy through manual
methods.

Theorem Proving Techniques

There are mul ple techniques used in theorem proving that help op mize
the process. These techniques include:
Backward Chaining: This is a technique where the theorem prover starts
by assuming the goal and then moves backward trying to derive the
prerequisites of the goal. This technique is widely used in automated
reasoning where the theorem to be proved is known beforehand.

Forward chaining: This is a technique where the theorem prover starts

with the axioms and moves forward trying to find a conclusion that
substan ates the hypothesis. In this method, the system generates all
possible conclusions based on the axioms un l it exhausts all the
possibili es and ul mately se les on the correct conclusion.

Resolu on: In this technique, the theorem prover a empts to prove a

theorem using contradic on. It does this by assuming the nega on of the
conjecture and then a empts to prove it is false. The theorem is
considered to be true if the assump on is proved to be false.

Challenges of Theorem Proving

Theorem proving is not without its challenges. Here are some of the
factors that make the task harder:

Complexity: Theorem proving can be a complex process, par cularly

when the statements involved are long and complex.

Scalability: Theorem proving is challenging to scale, especially if the

number of axioms and lemmas increases, making it hard to maintain or
even op mize its performance.

Ambiguity: The natural language used to state theorems can some mes
be ambiguous. This poses a challenge when transla ng the language into
a formal language that the theorem prover can process and understand.
What is NLP?
NLP stands for Natural Language Processing, which is a part of Computer Science, Human
language, and Artificial Intelligence. It is the technology that is used by machines to understand, analyse,
manipulate, and interpret human's languages. It helps developers to organize knowledge for performing tasks such
as translation, automatic summarization, Named Entity Recognition (NER), speech recognition,
relationship extraction, and topic segmentation.

History of NLP
(1940-1960) - Focused on Machine Translation (MT)
The Natural Languages Processing started in the year 1940s.
1948 - In the Year 1948, the first recognisable NLP application was introduced in Birkbeck College, London.
1950s - In the Year 1950s, there was a conflicting view between linguistics and computer science. Now, Chomsky
developed his first book syntactic structures and claimed that language is generative in nature.
In 1957, Chomsky also introduced the idea of Generative Grammar, which is rule based descriptions of syntactic
structures.
(1960-1980) - Flavored with Artificial Intelligence (AI)
In the year 1960 to 1980, the key developments were:
Augmented Transition Networks (ATN)
Augmented Transition Networks is a finite state machine that is capable of recognizing regular languages.
Case Grammar
Case Grammar was developed by Linguist Charles J. Fillmore in the year 1968. Case Grammar uses languages
such as English to express the relationship between nouns and verbs by using the preposition.
In Case Grammar, case roles can be defined to link certain kinds of verbs and objects.
For example: "Neha broke the mirror with the hammer". In this example case grammar identify Neha as an agent,
mirror as a theme, and hammer as an instrument.
In the year 1960 to 1980, key systems were:
SHRDLU
SHRDLU is a program written by Terry Winograd in 1968-70. It helps users to communicate with the computer
and moving objects. It can handle instructions such as "pick up the green boll" and also answer the questions like
"What is inside the black box." The main importance of SHRDLU is that it shows those syntax, semantics, and
reasoning about the world that can be combined to produce a system that understands a natural language.
LUNAR
LUNAR is the classic example of a Natural Language database interface system that is used ATNs and Woods'
Procedural Semantics. It was capable of translating elaborate natural language expressions into database queries
and handle 78% of requests without errors.
1980 - Current
Till the year 1980, natural language processing systems were based on complex sets of hand-written rules. After
1980, NLP introduced machine learning algorithms for language processing.
In the beginning of the year 1990s, NLP started growing faster and achieved good process accuracy, especially in
English Grammar. In 1990 also, an electronic text introduced, which provided a good resource for training and
examining natural language programs. Other factors may include the availability of computers with fast CPUs
and more memory. The major factor behind the advancement of natural language processing was the Internet.
Now, modern NLP consists of various applications, like speech recognition, machine translation, and machine
text reading. When we combine all these applications then it allows the artificial intelligence to gain knowledge
of the world. Let's consider the example of AMAZON ALEXA, using this robot you can ask the question to Alexa,
and it will reply to you.

Advantages of NLP
o NLP helps users to ask questions about any subject and get a direct response within seconds.
o NLP offers exact answers to the question means it does not offer unnecessary and unwanted information.
o NLP helps computers to communicate with humans in their languages.
o It is very time efficient.
o Most of the companies use NLP to improve the efficiency of documentation processes, accuracy of
documentation, and identify the information from large databases.
Disadvantages of NLP
A list of disadvantages of NLP is given below:
o NLP may not show context.
o NLP is unpredictable
o NLP may require more keystrokes.
o NLP is unable to adapt to the new domain, and it has a limited function that's why NLP is built for a single
and specific task only.
Components of NLP
There are the following two components of NLP -
1. Natural Language Understanding (NLU)(What do the user say?)
Natural Language Understanding (NLU) helps the machine to understand and analyse human language by
extracting the metadata from content such as concepts, entities, keywords, emotion, relations, and semantic roles.
NLU mainly used in Business applications to understand the customer's problem in both spoken and written
language.
NLU involves the following tasks -
o It is used to map the given input into useful representation.
o It is used to analyze different aspects of the language.
2. Natural Language Generation (NLG)(What should I say to the use?)
Natural Language Generation (NLG) acts as a translator that converts the computerized data into natural language
representation. It mainly involves Text planning, Sentence planning, and Text Realization.
Note: The NLU is difficult than NLG.
Difference between NLU and NLG

NLU NLG

NLU is the process of reading and interpreting NLG is the process of writing or generating language.
language.

It produces non-linguistic outputs from natural It produces constructing natural language outputs from non-
language inputs. linguistic inputs.

Applications of NLP
There are the following applications of NLP -
1. Question Answering
Question Answering focuses on building systems that automatically answer the questions asked by humans in a
natural language.
2. Spam Detection
Spam detection is used to detect unwanted e-mails getting to a user's inbox.

3. Sentiment Analysis
Sentiment Analysis is also known as opinion mining. It is used on the web to analyse the attitude, behaviour, and
emotional state of the sender. This application is implemented through a combination of NLP (Natural Language
Processing) and statistics by assigning the values to the text (positive, negative, or natural), identify the mood of
the context (happy, sad, angry, etc.)
4. Machine Translation
Machine translation is used to translate text or speech from one natural language to another natural language.

Example: Google Translator

5. Spelling correction
Microsoft Corporation provides word processor software like MS-word, PowerPoint for the spelling correction.

6. Speech Recognition
Speech recognition is used for converting spoken words into text. It is used in applications, such as mobile, home
automation, video recovery, dictating to Microsoft Word, voice biometrics, voice user interface, and so on.
7. Chatbot
Implementing the Chatbot is one of the important applications of NLP. It is used by many companies to provide
the customer's chat services.

8. Information extraction
Information extraction is one of the most important applications of NLP. It is used for extracting structured
information from unstructured or semi-structured machine-readable documents.
9. Natural Language Understanding (NLU)
It converts a large set of text into more formal representations such as first-order logic structures that are easier
for the computer programs to manipulate notations of the natural language processing.
How to build an NLP pipeline
There are the following steps to build an NLP pipeline -
Step1: Sentence Segmentation
Sentence Segment is the first step for building the NLP pipeline. It breaks the paragraph into separate sentences.
Example: Consider the following paragraph -
Independence Day is one of the important festivals for every Indian citizen. It is celebrated on the 15th of
August each year ever since India got independence from the British rule. The day celebrates independence
in the true sense.
Sentence Segment produces the following result:
1. "Independence Day is one of the important festivals for every Indian citizen."
2. "It is celebrated on the 15th of August each year ever since India got independence from the British rule."
3. "This day celebrates independence in the true sense."
Step2: Word Tokenization
Word Tokenizer is used to break the sentence into separate words or tokens.
Example:
JavaTpoint offers Corporate Training, Summer Training, Online Training, and Winter Training.
Word Tokenizer generates the following result:
"JavaTpoint", "offers", "Corporate", "Training", "Summer", "Training", "Online", "Training", "and", "Winter",
"Training", "."
Step3: Stemming
Stemming is used to normalize words into its base form or root form. For example, celebrates, celebrated and
celebrating, all these words are originated with a single root word "celebrate." The big problem with stemming is
that sometimes it produces the root word which may not have any meaning.
For Example, intelligence, intelligent, and intelligently, all these words are originated with a single root word
"intelligen." In English, the word "intelligen" do not have any meaning.
Step 4: Lemmatization
Lemmatization is quite similar to the Stemming. It is used to group different inflected forms of the word, called
Lemma. The main difference between Stemming and lemmatization is that it produces the root word, which has
a meaning.
For example: In lemmatization, the words intelligence, intelligent, and intelligently has a root word intelligent,
which has a meaning.
Step 5: Identifying Stop Words
In English, there are a lot of words that appear very frequently like "is", "and", "the", and "a". NLP pipelines will
flag these words as stop words. Stop words might be filtered out before doing any statistical analysis.
Example: He is a good boy.
Note: When you are building a rock band search engine, then you do not ignore the word "The."
Step 6: Dependency Parsing
Dependency Parsing is used to find that how all the words in the sentence are related to each other.
Step 7: POS tags
POS stands for parts of speech, which includes Noun, verb, adverb, and Adjective. It indicates that how a word
functions with its meaning as well as grammatically within the sentences. A word has one or more parts of speech
based on the context in which it is used.
Example: "Google" something on the Internet.
In the above example, Google is used as a verb, although it is a proper noun.
Step 8: Named Entity Recognition (NER)
Named Entity Recognition (NER) is the process of detecting the named entity such as person name, movie name,
organization name, or location.
Example: Steve Jobs introduced iPhone at the Macworld Conference in San Francisco, California.
Step 9: Chunking
Chunking is used to collect the individual piece of information and grouping them into bigger pieces of sentences.
Phases of NLP
There are the following five phases of NLP:

1. Lexical Analysis and Morphological

The first phase of NLP is the Lexical Analysis. This phase scans the source code as a stream of characters and
converts it into meaningful lexemes. It divides the whole text into paragraphs, sentences, and words.
2. Syntactic Analysis (Parsing)
Syntactic Analysis is used to check grammar, word arrangements, and shows the relationship among the words.
Example: Agra goes to the Poonam
In the real world, Agra goes to the Poonam, does not make any sense, so this sentence is rejected by the Syntactic
analyzer.
3. Semantic Analysis
Semantic analysis is concerned with the meaning representation. It mainly focuses on the literal meaning of words,
phrases, and sentences.
4. Discourse Integration
Discourse Integration depends upon the sentences that proceeds it and also invokes the meaning of the sentences
that follow it.
5. Pragmatic Analysis
Pragmatic is the fifth and last phase of NLP. It helps you to discover the intended effect by applying a set of rules
that characterize cooperative dialogues.
For Example: "Open the door" is interpreted as a request instead of an order.
Why NLP is difficult?
NLP is difficult because Ambiguity and Uncertainty exist in the language.
Ambiguity
There are the following three ambiguity -
o Lexical Ambiguity
Lexical Ambiguity exists in the presence of two or more possible meanings of the sentence within a single word.
Example:
Manya is looking for a match.
In the above example, the word match refers to that either Manya is looking for a partner or Manya is looking for
a match. (Cricket or other match)
o Syntactic Ambiguity
Syntactic Ambiguity exists in the presence of two or more possible meanings within the sentence.
Example:
I saw the girl with the binocular.
In the above example, did I have the binoculars? Or did the girl have the binoculars?
o Referential Ambiguity
Referential Ambiguity exists when you are referring to something using the pronoun.
Example: Kiran went to Sunita. She said, "I am hungry."
In the above sentence, you do not know that who is hungry, either Kiran or Sunita.
NLP Libraries
Scikit-learn: It provides a wide range of algorithms for building machine learning models in Python.
Natural language Toolkit (NLTK): NLTK is a complete toolkit for all NLP techniques.
Pattern: It is a web mining module for NLP and machine learning.
TextBlob: It provides an easy interface to learn basic NLP tasks like sentiment analysis, noun phrase extraction,
or pos-tagging.
Quepy: Quepy is used to transform natural language questions into queries in a database query language.
SpaCy: SpaCy is an open-source NLP library which is used for Data Extraction, Data Analysis, Sentiment
Analysis, and Text Summarization.
Gensim: Gensim works with large datasets and processes data streams.
Difference between Natural language and Computer Language

Natural Language Computer Language

Natural language has a very large vocabulary. Computer language has a very limited vocabulary.

Natural language is easily understood by humans. Computer language is easily understood by the machines.

Natural language is ambiguous in nature. Computer language is unambiguous.

Computer vision is a subfield of artificial intelligence that deals with acquiring, processing, analyzing, and making sense
of visual data such as digital images and videos. It is one of the most compelling types of artificial intelligence that we
regularly implement in our daily routines.
Computer vision helps to understand the complexity of the human vision system and trains computer systems to interpret
and gain a high-level understanding of digital images or videos. In the early days, developing a machine system having
human-like intelligence was just a dream, but with the advancement of artificial intelligence and machine learning, it also
became possible. Similarly, such intelligent systems have been developed that can "see" and interpret the world around
them, similar to human eyes. The fiction of yesterday has become the fact of today.
Further, Artificial intelligence is the branch of computer science that primarily deals with creating a smart and intelligent
system that can behave and think like the human brain. So, we can say if artificial intelligence enables computer systems to
think intelligently, computer vision makes them capable of seeing, analyzing, and understanding.
How does Computer Vision Work?
Computer vision is a technique that extracts information from visual data, such as images and videos. Although computer
vision works similarly to human eyes with brain work, this is probably one of the biggest open questions for IT professionals:
How does the human brain operate and solve visual object recognition?

On a certain level, computer vision is all about pattern recognition which includes the training process of machine systems
for understanding the visual data such as images and videos, etc.
Firstly, a vast amount of visual labeled data is provided to machines to train it. This labeled data enables the machine to
analyze different patterns in all the data points and can relate to those labels. E.g., suppose we provide visual data of millions
of dog images. In that case, the computer learns from this data, analyzes each photo, shape, the distance between each shape,
color, etc., and hence identifies patterns similar to dogs and generates a model. As a result, this computer vision model can
now accurately detect whether the image contains a dog or not for each input image.
Task Associated with Computer Vision
Although computer vision has been utilized in so many fields, there are a few common tasks for computer vision systems.
These tasks are given below:

o Object classification: Object classification is a computer vision technique/task used to classify an image, such as
whether an image contains a dog, a person's face, or a banana. It analyzes the visual content (videos & images) and
classifies the object into the defined category. It means that we can accurately predict the class of an object present
in an image with image classification.
o Object Identification/detection: Object identification or detection uses image classification to identify and locate
the objects in an image or video. With such detection and identification technique, the system can count objects in
a given image or scene and determine their accurate location and labeling. For example, in a given image, one dog,
one cat, and one duck can be easily detected and classified using the object detection technique.
o Object Verification: The system processes videos, finds the objects based on search criteria, and tracks their
movement.
o Object Landmark Detection: The system defines the key points for the given object in the image data.
o Image Segmentation: Image segmentation not only detects the classes in an image as image classification; instead,
it classifies each pixel of an image to specify what objects it has. It tries to determine the role of each pixel in the
image.
o Object Recognition: In this, the system recognizes the object's location with respect to the image.
How to learn computer Vision?
Although, computer vision requires all basic concepts of machine learning, deep learning, and artificial intelligence. But if
you are eager to learn computer vision, then you must follow below things, which are as follows:
1. Build your foundation:
o Before entering this field, you must have strong knowledge of advanced mathematical concepts such as
Probability, statistics, linear algebra, calculus, etc.
o The knowledge of programming languages like Python would be an extra advantage to getting started with
this domain.

2. Digital Image Processing:

It would be best if you understood image editing tools and their functions, such as histogram equalization, median
 filtering, etc. Further, you should also know about compressing images and videos using JPEG and MPEG files.
Once you know the basics of image processing and restoration, you can kick-start your journey into this domain.
3. Machine learning understanding
To enter this domain, you must deeply understand basic machine learning concepts such as CNN, neural
networks, SVM, recurrent neural networks, generative adversarial neural networks, etc.
4. Basic computer vision: This is the step where you need to decrypt the mathematical models used in visual data
formulation.
Applications of computer vision
Computer vision is one of the most advanced innovations of artificial intelligence and machine learning. As per the
increasing demand for AI and Machine Learning technologies, computer vision has also become a center of attraction among
different sectors. It greatly impacts different industries, including retail, security, healthcare, automotive, agriculture, etc.
Below are some most popular applications of computer vision:
o Facial recognition: Computer vision has enabled machines to detect face images of people to verify their identity.
Initially, the machines are given input data images in which computer vision algorithms detect facial features and
compare them with databases of fake profiles. Popular social media platforms like Facebook also use facial
recognition to detect and tag users. Further, various government spy agencies are employing this feature to identify
criminals in video feeds.
o Healthcare and Medicine: Computer vision has played an important role in the healthcare and medicine industry.
Traditional approaches for evaluating cancerous tumors are time-consuming and have less accurate predictions,
whereas computer vision technology provides faster and more accurate chemotherapy response assessments;
doctors can identify cancer patients who need faster surgery with life-saving precision.
o Self-driving vehicles: Computer vision technology has also contributed to its role in self-driving vehicles to make
sense of their surroundings by capturing video from different angles around the car and then introducing it into the
software. This helps to detect other cars and objects, read traffic signals, pedestrian paths, etc., and safely drive its
passengers to their destination.
o Optical character recognition (OCR)
Optical character recognition helps us extract printed or handwritten text from visual data such as images. Further,
it also enables us to extract text from documents like invoices, bills, articles, etc.
o Machine inspection: Computer vision is vital in providing an image-based automatic inspection. It detects a
machine's defects, features, and functional flaws, determines inspection goals, chooses lighting and material-
handling techniques, and other irregularities in manufactured products.
o Retail (e.g., automated checkouts): Computer vision is also being implemented in the retail industries to track
products, shelves, wages, record product movements into the store, etc. This AI-based computer vision technique
automatically charges the customer for the marked products upon checkout from the retail stores.
o 3D model building: 3D model building or 3D modeling is a technique to generate a 3D digital representation of
any object or surface using the software. In this field also, computer vision plays its role in constructing 3D computer
models from existing objects. Furthermore, 3D modeling has a variety of applications in various places, such as
Robotics, Autonomous driving, 3D tracking, 3D scene reconstruction, and AR/VR.
o Medical imaging: Computer vision helps medical professionals make better decisions regarding treating patients
by developing visualization of specific body parts such as organs and tissues. It helps them get more accurate
diagnoses and a better patient care system. E.g., Computed Tomography (CT) or Magnetic Resonance Imaging
(MRI) scanner to diagnose pathologies or guide medical interventions such as surgical planning or for research
purposes.
 o Automotive safety: Computer vision has added an important safety feature in automotive industries. E.g., if a
vehicle is taught to detect objects and dangers, it could prevent an accident and save thousands of lives and property.
o Surveillance: It is one of computer vision technology's most important and beneficial use cases. Nowadays, CCTV
cameras are almost fitted in every place, such as streets, roads, highways, shops, stores, etc., to spot various doubtful
or criminal activities. It helps provide live footage of public places to identify suspicious behavior, identify
dangerous objects, and prevent crimes by maintaining law and order.
o Fingerprint recognition and biometrics: Computer vision technology detects fingerprints and biometrics to
validate a user's identity. Biometrics deals with recognizing persons based on physiological characteristics, such as
the face, fingerprint, vascular pattern, or iris, and behavioral traits, such as gait or speech. It combines Computer
Vision with knowledge of human physiology and behavior.
Which programming language is best for computer vision?
Computer vision engineers require in-depth knowledge of machine learning and deep learning concepts with strong
command over at least one programming language. There are so many programming languages that can be used in this
domain, but Python is among the most popular. However, one can also choose OpenCV with Python, OpenCV with C++,
or MATLAB to learn and implement computer vision applications.
OpenCV with Python could be the most preferred choice for beginners due to its flexibility, simple syntax, and versatility.
Various reasons make Python the best programming language for computer vision, which is as follows:
o Easy-to-use: Python is very famous as it is easy to learn for entry-level persons and professionals. Further, Python
is also easily adaptable and covers all business needs.
o Most used programming language: Python is one of the most popular programming languages as it contains
complete learning environments to get started with machine learning, artificial intelligence, deep learning, and
computer vision.
o Debugging and visualization: Python has an in-built facility for debugging via 'PDB' and visualization through
Matplotlib.
Computer Vision Challenges
Computer vision has emerged as one of the most growing domains of artificial intelligence, but it still has a few challenges
to becoming a leading technology. There are a few challenges observed while working with computer vision technology.
o Reasoning and analytical issues: All programming languages and technologies require the basic logic behind any
task. To become a computer vision expert, you must have strong reasoning and analytical skills. If you don't have
such skills, then defining any attribute in visual content may be a big problem.
o Privacy and security: Privacy and security are among the most important factors for any country. Similarly, vision-
powered surveillance is also having various serious privacy issues for lots of countries. It restricts users from
accessing unauthorized content. Further, various countries also avoid such face recognition and detection techniques
for privacy and security reasons.
o Duplicate and false content: Cyber security is always a big concern for all organizations, and they always try to
protect their data from hackers and cyber fraud. A data breach can lead to serious problems, such as creating
duplicate images and videos over the internet.
 Top Computer Vision Techniques
1. Image Classification
o Image classification is the simplest technique of Computer Vision. The main aim of image classification
is to classify the image into one or more different categories. Image classifier basically takes an image as
input and tells about different objects present in that image, such as a person, dog, tree, etc. However, it
would not give you other more information about the image data, such as how many persons are there,
tree colour, item positions, etc., and for this, we need to go for any other CV technique.
o
2. Object Detection
o Object detection is another popular technique of computer vision that can be performed after Image
classification or which uses image classification to detect the objects in visual data. It is basically used to
recognize the objects within the boundary boxes and find the class of the objects in the image. Object
detection makes use of deep learning and machine learning technology to generate useful results.

3. Semantic Segmentation
o Semantic Segmentation is not only about detecting the classes in an image as image classification. Instead,
it classifies each pixel of an image to specify what objects it has. It tries to determine the role of each pixel
in the image. It basically classifies pixelS in a particular category without differentiating the object
instances. Or we can say it classifies similar objects as a single class from the pixel levels. For example,
if an image contains two dogs, then semantic segmentation will put both the dogs under the same label. It
tries to understand the role of each pixel in an image.
o
4. Instance Segmentation
o Instance segmentation can classify the objects in an image at pixel level as similar to semantic
segmentation but with a more advanced level. It means Instance Segmentation can classify similar types
of objects into different categories. For example, if visual consists of various cars, then with semantic
segmentation, we can tell that there are multiple cars, but with instance segmentation, we can label them
according to their colour, shape, etc.

5. Panoptic Segmentation
o Panoptic Segmentation is one of the most powerful computer vision techniques as it combines the Instance
and Semantic Segmentation techniques. It means with Panoptic Segmentation, you can classify image
objects at pixel levels and can also identify separate instances of that class.
 6. Keypoint Detection
o Keypoint detection tries to detect some key points in an image to give more details about a class of objects.
It basically detects people and localizes their key points. There are mainly two keypoint detection areas,
which are Body Keypoint Detection and Facial Keypoint Detection.
o For example, Facial keypoint detection includes detecting key parts of the human face such as the nose,
eyes, corners, eyebrows, etc. Keypoint detection mainly has applications, including face detection, pose
detection, etc.

7. Person Segmentation
o Person segmentation is a type of image segmentation technique which is used to separate the person from
the background within an image. It can be used after the pose estimation, as with this, we can closely
identify the exact location of the person in the image as well as the pose of that person.

8. Depth Perception
Depth perception is a computer vision technique that provides the visual ability to machines to estimate
the 3D depth/distance of an object from the source. Depth Perception has wide applications, including the
Reconstruction of objects in Augmented Reality, Robotics, self-driving cars, etc. LiDAR(Lights
Detection and Ranging) is one of the popular techniques that is used for in-depth perception. With the
help of laser beams, it measures the relative distance of an object by illuminating it with laser light and
then measuring the reflections using sensors.

9. Image Captioning
o Image captioning, as the name suggests, is about giving a suitable caption to the image that can describe
the image. It makes use of neural networks, where when we input an image, then it generates a caption for
that image that can easily describe the image. It is not only the task of Computer vision but also an NLP
task.

10. 3D Object Reconstruction

o As the name suggests, 3D object reconstruction is a technique that can extract 3D objects from a 2D image.
Currently, it is a much-developing field of computer vision, and it can be done in different ways for
different objects. On this technique, one of the most successful papers is PiFuHD, which tells about 3D
human digitization.
Speech Recognition in Artificial Intelligence
The way people interact with digital gadgets and systems has changed dramatically in recent years due to
noteworthy developments in speech recognition technology. Speech recognition is a crucial component of
artificial intelligence (AI) that helps close the communication gap between people and machines. Automation,
accessibility features, virtual assistants, transcription services, and other uses for machine understanding and
interpretation of spoken language are made possible by this technology. The intriguing field of voice recognition
in artificial intelligence, along with its services, difficulties, and prospects, will all be covered in this article.
Developing Knowledge of Speech Recognition
Speech recognition technology, also known as Automatic Speech Recognition (ASR), makes it possible for
computers and artificial intelligence (AI) systems to translate spoken words into text. There are several steps in
this process:
1. Decoding: Based on the data obtained in the above processes, the last step includes choosing the most
probable translation for the spoken words.
2. Feature extraction: In this stage, the audio input is processed to extract characteristics such as Mel-
frequency cepstral coefficients (MFCCs), which give the system the necessary information to recognize
the sound.
3. Acoustic Analysis: The audio signal is captured by the system, which then dissects it into its constituent
elements, such as prosody and phonemes.
4. Language Modeling: To increase recognition accuracy, language models are used to comprehend the
semantics and grammatical structure of spoken words.
5. Acoustic Modeling: To link the retrieved characteristics with recognized phonetic patterns and language
context, the system applies statistical models.
What exactly is Speech Recognition in AI?
The technique of recognizing a human voice is known as speech recognition. To detect speech, firms usually
develop these programs and incorporate them into different hardware devices. The software will react correctly
when it hears your voice or gets your command.
Many companies use cutting-edge technology like artificial intelligence, machine learning, and neural networks
to develop voice recognition software. Technologies like Cortana, Alexa, Siri and Google Assistant have altered
how people use electronics and technology. They include automobiles, cell phones, home security systems, and
more.
Recall that speech and voice recognition are two different things. Speech recognition translates spoken words into
text by first identifying them in an audio recording of a speaker. On the other hand, speech recognition can only
identify pre-programmed spoken instructions. The sole commonality between these two approaches is the
conversion of sound to text.
How AI Handles Speech Recognition?
Automatic speech recognition (ASR), sometimes referred to as speech recognition in AI, is a sophisticated method
that allows robots to translate spoken language into text or other forms that are comprehensible. Speech
recognition technology consists of several steps and parts. Here's a summary of how it functions:
1. Audio Input: A microphone is usually used to record the audio input, which starts the process. Any
spoken human speech, including commands and conversations, can be used as this audio input.
2. Preprocessing: To enhance its quality and prepare it for analysis, the raw audio signal is preprocessed.
This might be signal amplification, noise reduction, or other methods to improve the audio data.
3. Language Modeling: Language models are used to comprehend the semantics and grammatical structure
of spoken words. By assisting the system in understanding the context and connections between words,
these models increase the accuracy of word recognition. When it comes to managing homophones?words
that sound identically but have distinct meanings-and the order of words and sentence structure changes,
language modelling is incredibly crucial.
4. Decoding: By integrating the data from the acoustic and linguistic models, the system decodes the spoken
words. It assesses several word combinations and determines which transcription is more plausible based
on statistical probability.
5. Output: The recognized language or a command that may be applied to several different situations is the
ultimate output. This output can be utilized for transcription, operating a device, giving instructions to a
virtual assistant, and other similar tasks.
Speech Recognition AI and Natural Language Processing
Recognition of Speech Machines can now comprehend and interpret human language thanks to the closely
connected sciences of artificial intelligence (AI) and natural language processing (NLP). NLP covers various
applications, such as language translation, sentiment analysis, and text summarization, whereas voice recognition
AI concentrates on translating spoken words into digital text or commands.
Making it possible for robots to comprehend and interpret human language similarly to how humans do is one of
the main objectives of natural language processing (NLP). This entails knowing the broader context and meaning
of the words and recognizing them individually. For instance, depending on the situation, "I saw a bat" might
mean several things. Either the animal or a piece of athletic gear might be the subject.
AI for speech recognition is a branch of natural language processing (NLP) specializing in translating spoken
utterances into digital text and commands. Speech recognition artificial intelligence (AI) systems employ
sophisticated algorithms to map speech patterns to phonetic units, analyze and interpret speech patterns, and
generate statistical models that represent sounds to do this.
Among the methods employed by AI to recognize speech are:
o Deep Neural Networks (DNNs): Used widely in voice recognition artificial intelligence, DNNs are a
machine learning model. DNNs represent intricate links between the speech input and the associated text
output by employing a hierarchy of layers.
o Hidden Markov Models (HMMs): AI voice recognition uses Hidden Markov Models (HMMs), which
are statistical models. To match input speech to the most likely sound sequence, HMMs first model the
probability distribution of speech sounds.
o Convolutional Neural Networks (CNNs): Artificial Intelligence for speech recognition has also made
use of Convolutional Neural Networks (CNNs), a class of machine learning model that is frequently
employed in image recognition. To find pertinent characteristics, CNNs process incoming speech signals
by applying filters.
Among the most recent developments in AI voice recognition are:
o End-to-end models: These models are made to translate speech impulses directly into text, eliminating
the need for any intermediary stages. These models have demonstrated the potential for raising voice
recognition AI's precision and effectiveness.
o Multimodal models: These enable more intuitive and natural interactions between machines and humans
by fusing voice recognition Intelligence with other modalities, including vision or touch.
o Transformer-based models: BERT and GPT are two examples of transformer-based models that have
shown great success in tasks related to natural language processing and are now being used in artificial
intelligence for voice recognition.
o Data augmentation: Increasing the data used for training for speech recognition AI models will increase
their accuracy and resilience. Data augmentation strategies include introducing background noise and
modifying the speaking tempo.

Difficulties with Speech Recognition

Even though voice recognition technology has advanced significantly, several issues still exist:
1. Accuracy: It still needs to be improved to recognize speech with great precision, particularly in loud
surroundings or when there are a variety of accents.
 2. Privacy Concerns: As speech-recognizing technologies are incorporated into more aspects of daily life,
privacy issues about the gathering and using voice data have surfaced.
3. Context Understanding: The field of interpreting spoken language's context and intent is still
developing. AI systems frequently have trouble understanding complex or unclear instructions.
4. Speaker Variability: It might be challenging to distinguish speech from various speakers and adjust to
differing accents and speaking tenor.
Applications of AI for Speech Recognition
In many domains and uses, artificial intelligence is used as a commercial solution for speech recognition. Voice-
activated audio content assistants, call centres, ATMs, and more benefit from AI's more natural user interactions
with hardware and software and its increased accuracy in data transcription.
1. Telecommunications: Speech recognition models offer more efficient call handling and analysis. Better
customer service frees agents to focus on what makes them most valuable. Thanks to the availability of
text messaging and voice transcription services, customers can now contact companies in real-time,
around-the-clock, which enhances their entire experience and makes them feel more connected to the
company.
2. Medical: Voice-activated Artificial Intelligence is becoming more prevalent in the telecommunications
industry. Speech recognition technology models provide more efficient call handling and analysis. Better
customer service frees agents to focus on what makes them most valuable.
3. Banking: Dialogue Financial and banking organizations utilize AI apps to help customers with their
business questions. You may ask a bank, for example, for information on your savings account's current
interest rate or account balance. Because they no longer need to perform in-depth research or access cloud
data, customer service representatives can reply to requests more rapidly and offer more outstanding
assistance.
4. Automotive Voice Commands: Hands-free voice control of amenities like climate control, entertainment
systems, and navigation is a common feature of modern vehicles.
Finally, A potent commercial product called speech recognition makes it possible for computers, apps, and
software to comprehend spoken language and translate it into text. This technology understands what you say and
precisely reproduces them as written data on a screen using artificial intelligence (AI) to analyze your voice and
language. Feature extraction, Signal processing, language modelling, and decoding are some of the crucial
elements in the process.
Artificial Intelligence voice recognition essentially converts spoken words to digital signals that are interpreted
and analyzed by robots. Natural language processing (NLP), which allows machines to comprehend and interpret
human language, is closely related to this skill. By enabling computers to carry out a variety of language-related
activities, including text summarization, sentiment analysis, and language translation, natural language processing
(NLP) expands the capabilities of voice recognition. Together, voice recognition and natural language processing
(NLP) is propelling the creation of more user-friendly and engaging human-machine interfaces, which will
ultimately improve our capacity to connect with and teach technology through spoken language.
Robotics:
Robotics is a separate entity in Artificial Intelligence that helps study the creation of intelligent robots or machines.
Robotics combines electrical engineering, mechanical engineering and computer science & engineering as they
have mechanical construction, electrical component and programmed with programming language. Although,
Robotics and Artificial Intelligence both have different objectives and applications, but most people treat robotics
as a subset of Artificial Intelligence (AI). Robot machines look very similar to humans, and also, they can perform
like humans, if enabled with AI.
What is a robot?
A robot is a machine that looks like a human, and is capable of performing out of box actions and replicating
certain human movements automatically by means of commands given to it using programming. Examples: Drug
Compounding Robot, Automotive Industry Robots, Order Picking Robots, Industrial Floor Scrubbers and Sage
Automation Gantry Robots, etc.
Components of Robot
Several components construct a robot, these components are as follows:

o Actuators: Actuators are the devices that are responsible for moving and controlling a system or machine.
It helps to achieve physical movements by converting energy like electrical, hydraulic and air, etc.
Actuators can create linear as well as rotary motion.
o Power Supply: It is an electrical device that supplies electrical power to an electrical load. The primary
function of the power supply is to convert electrical current to power the load.
o Electric Motors: These are the devices that convert electrical energy into mechanical energy and are
required for the rotational motion of the machines.
 o Pneumatic Air Muscles: Air Muscles are soft pneumatic devices that are ideally best fitted for robotics.
They can contract and extend and operate by pressurized air filling a pneumatic bladder. Whenever air is
introduced, it can contract up to 40%.
o Muscles wire: These are made up of nickel-titanium alloy called Nitinol and are very thin in shape. It can
also extend and contract when a specific amount of heat and electric current is supplied into it. Also, it
can be formed and bent into different shapes when it is in its martensitic form. They can contract by 5%
when electrical current passes through them.
o Piezo Motors and Ultrasonic Motors: Piezoelectric motors or Piezo motors are the electrical devices that
receive an electric signal and apply a directional force to an opposing ceramic plate. It helps a robot to
move in the desired direction. These are the best suited electrical motors for industrial robots.
o Sensor: They provide the ability like see, hear, touch and movement like humans. Sensors are the devices
or machines which help to detect the events or changes in the environment and send data to the computer
processor. These devices are usually equipped with other electronic devices. Similar to human organs, the
electrical sensor also plays a crucial role in Artificial Intelligence & robotics. AI algorithms control robots
by sensing the environment, and it provides real-time information to computer processors.

Applications of Robotics
Robotics have different application areas. Some of the important applications domains of robotics are as follows:
o Robotics in defense sectors: The defense sector is undoubtedly the one of the main parts of any country.
Each country wants their defense system to be strong. Robots help to approach inaccessible and dangerous
zone during war. DRDO has developed a robot named Daksh to destroy life-threatening objects safely.
They help soldiers to remain safe and deployed by the military in combat scenarios. Besides combat
support, robots are also deployed in anti-submarine operations, fire support, battle damage management,
strike missions, and laying machines.
o Robotics in Medical sectors: Robots also help in various medical fields such as laparoscopy, neurosurgery,
orthopaedic surgery, disinfecting rooms, dispensing medication, and various other medical domains.
o Robotics in Industrial Sector: Robots are used in various industrial manufacturing industries such as
cutting, welding, assembly, disassembly, pick and place for printed circuit boards, packaging & labelling,
palletizing, product inspection & testing, colour coating, drilling, polishing and handling the materials.
Moreover, Robotics technology increases productivity and profitability and reduces human efforts,
resulting from lower physical strain and injury. The industrial robot has some important advantages, which
are as follows:
o Accuracy
o Flexibility
o Reduced labour charge
o Low noise operation
o Fewer production damages
o Increased productivity rate.
 o Robotics in Entertainment: Over the last decade, use of robots is continuously getting increased in
entertainment areas. Robots are being employed in entertainment sector, such as movies, animation, games
and cartoons. Robots are very helpful where repetitive actions are required. A camera-wielding robot helps
shoot a movie scene as many times as needed without getting tired and frustrated. A big-name Disney has
launched hundreds of robots for the film industry.
o Robots in the mining industry: Robotics is very helpful for various mining applications such as robotic
dozing, excavation and haulage, robotic mapping & surveying, robotic drilling and explosive handling,
etc. A mining robot can solely navigate flooded passages and use cameras and other sensors to detect
valuable minerals. Further, robots also help in excavation to detect gases and other materials and keep
humans safe from harm and injuries. The robot rock climbers are used for space exploration, and
underwater drones are used for ocean exploration.

AI technology used in Robotics

Computer Vision
Robots can also see, and this is possible by one of the popular Artificial Intelligence technologies named Computer
vision. Computer Vision plays a crucial role in all industries like health, entertainment, medical, military, mining,
etc.
Computer Vision is an important domain of Artificial Intelligence that helps in extracting meaningful information
from images, videos and visual inputs and take action accordingly.
Natural Language Processing
NLP (Natural Languages Processing) can be used to give voice commands to AI robots. It creates a strong human-
robot interaction. NLP is a specific area of Artificial Intelligence that enables the communication between humans
and robots. Through the NLP technique, the robot can understand and reproduce human language. Some robots
are equipped with NLP so that we can't differentiate between humans and robots.
Similarly, in the health care sector, robots powered by Natural Language Processing may help physicians to
observe the decease details and automatically fill in EHR. Besides recognizing human language, it can learn
common uses, such as learn the accent, and predict how humans speak.
Edge Computing
Edge computing in robots is defined as a service provider of robot integration, testing, design and simulation.
Edge computing in robotics provides better data management, lower connectivity cost, better security practices,
more reliable and uninterrupted connection.
Complex Event Process
Complex event processing (CEP) is a concept that helps us to understand the processing of multiple events in real
time. An event is described as a Change of State, and one or more events combine to define a Complex event.
The complex event process is most widely used term in various industries such as healthcare, finance, security,
marketing, etc. It is primarily used in credit card fraud detection and also in stock marketing field.
For example, the deployment of an airbag in a car is a complex event based on the data from multiple sensors in
real-time. This idea is used in Robotics, for example, Event-Processing in Autonomous Robot Programming.
Transfer Learning and AI
This is the technique used to solve a problem with the help of another problem that is already solved. In Transfer
learning technique, knowledge gained from solving one problem can be implement to solve related problem. We
can understand it with an example such as the model used for identifying a circle shape can also be used to identify
a square shape.
Transfer learning reuses the pre-trained model for a related problem, and only the last layer of the model is trained,
which is relatively less time consuming and cheaper. In robotics, transfer learning can be used to train one machine
with the help of other machines.
Reinforcement Learning
Reinforcement learning is a feedback-based learning method in machine learning that enables an AI agent to learn
and explore the environment, perform actions and learn automatically from experience or feedback for each
action. Further, it is also having feature of autonomously learn to behave optimally through hit-and-trail action
while interacting with the environment. It is primarily used to develop the sequence of decisions and achieve the
goals in uncertain and potentially complex environment. In robotics, robots explore the environment and learn
about it through hit and trial. For each action, he gets rewarded (positive or negative). Reinforcement learning
provides Robotics with a framework to design and simulate sophisticated and hard-to-engineer behaviours.
Affective computing
Affective computing is a field of study that deals with developing systems that can identify, interpret, process,
and simulate human emotions. Affective computing aims to endow robots with emotional intelligence to hope
that robots can be endowed with human-like capabilities of observation, interpretation, and emotion expression.
Mixed Reality
Mixed Reality is also an emerging domain. It is mainly used in the field of programming by demonstration (PbD).
PbD creates a prototyping mechanism for algorithms using a combination of physical and virtual objects.
What is an Expert System?
An expert system is a computer program that is designed to solve complex problems and to provide decision-
making ability like a human expert. It performs this by extracting knowledge from its knowledge base using the
reasoning and inference rules according to the user queries.
The expert system is a part of AI, and the first ES was developed in the year 1970, which was the first successful
approach of artificial intelligence. It solves the most complex issue as an expert by extracting the knowledge
stored in its knowledge base. The system helps in decision making for complex problems using both facts and
heuristics like a human expert. It is called so because it contains the expert knowledge of a specific domain and
can solve any complex problem of that particular domain. These systems are designed for a specific domain, such
as medicine, science, etc.
The performance of an expert system is based on the expert's knowledge stored in its knowledge base. The more
knowledge stored in the KB, the more that system improves its performance. One of the common examples of an
ES is a suggestion of spelling errors while typing in the Google search box.
Below is the block diagram that represents the working of an expert system:

Note: It is important to remember that an expert system is not used to replace the human experts; instead, it is
used to assist the human in making a complex decision. These systems do not have human capabilities of thinking
and work on the basis of the knowledge base of the particular domain.
Below are some popular examples of the Expert System:
o DENDRAL: It was an artificial intelligence project that was made as a chemical analysis expert system.
It was used in organic chemistry to detect unknown organic molecules with the help of their mass spectra
and knowledge base of chemistry.
 o MYCIN: It was one of the earliest backward chaining expert systems that was designed to find the bacteria
causing infections like bacteraemia and meningitis. It was also used for the recommendation of antibiotics
and the diagnosis of blood clotting diseases.
o PXDES: It is an expert system that is used to determine the type and level of lung cancer. To determine
the disease, it takes a picture from the upper body, which looks like the shadow. This shadow identifies
the type and degree of harm.
o CaDeT: The CaDet expert system is a diagnostic support system that can detect cancer at early stages.
Characteristics of Expert System
o High Performance: The expert system provides high performance for solving any type of complex
problem of a specific domain with high efficiency and accuracy.
o Understandable: It responds in a way that can be easily understandable by the user. It can take input in
human language and provides the output in the same way.
o Reliable: It is much reliable for generating an efficient and accurate output.
o Highly responsive: ES provides the result for any complex query within a very short period of time.
Components of Expert System
An expert system mainly consists of three components:
o User Interface
o Inference Engine
o Knowledge Base
 1. User Interface
With the help of a user interface, the expert system interacts with the user, takes queries as an input in a readable
format, and passes it to the inference engine. After getting the response from the inference engine, it displays the
output to the user. In other words, it is an interface that helps a non-expert user to communicate with the expert
system to find a solution.
2. Inference Engine(Rules of Engine)
o The inference engine is known as the brain of the expert system as it is the main processing unit of the
system. It applies inference rules to the knowledge base to derive a conclusion or deduce new information.
It helps in deriving an error-free solution of queries asked by the user.
o With the help of an inference engine, the system extracts the knowledge from the knowledge base.
o There are two types of inference engine:
o Deterministic Inference engine: The conclusions drawn from this type of inference engine are assumed to
be true. It is based on facts and rules.
o Probabilistic Inference engine: This type of inference engine contains uncertainty in conclusions, and
based on the probability.
Inference engine uses the below modes to derive the solutions:
o Forward Chaining: It starts from the known facts and rules, and applies the inference rules to add their
conclusion to the known facts.
o Backward Chaining: It is a backward reasoning method that starts from the goal and works backward to
prove the known facts.
3. Knowledge Base
o The knowledgebase is a type of storage that stores knowledge acquired from the different experts of the
particular domain. It is considered as big storage of knowledge. The more the knowledge base, the more
precise will be the Expert System.
o It is similar to a database that contains information and rules of a particular domain or subject.
o One can also view the knowledge base as collections of objects and their attributes. Such as a Lion is an
object and its attributes are it is a mammal, it is not a domestic animal, etc.
Components of Knowledge Base
o Factual Knowledge: The knowledge which is based on facts and accepted by knowledge engineers comes
under factual knowledge.
o Heuristic Knowledge: This knowledge is based on practice, the ability to guess, evaluation, and
experiences.
Knowledge Representation: It is used to formalize the knowledge stored in the knowledge base using the If-else
rules.
Knowledge Acquisitions: It is the process of extracting, organizing, and structuring the domain knowledge,
specifying the rules to acquire the knowledge from various experts, and store that knowledge into the knowledge
base.
Development of Expert System
Here, we will explain the working of an expert system by taking an example of MYCIN ES. Below are some
steps to build an MYCIN:
o Firstly, ES should be fed with expert knowledge. In the case of MYCIN, human experts specialized in the
medical field of bacterial infection, provide information about the causes, symptoms, and other knowledge
in that domain.
o The KB of the MYCIN is updated successfully. In order to test it, the doctor provides a new problem to
it. The problem is to identify the presence of the bacteria by inputting the details of a patient, including
the symptoms, current condition, and medical history.
o The ES will need a questionnaire to be filled by the patient to know the general information about the
patient, such as gender, age, etc.
o Now the system has collected all the information, so it will find the solution for the problem by applying
if-then rules using the inference engine and using the facts stored within the KB.
o In the end, it will provide a response to the patient by using the user interface.
Participants in the development of Expert System
There are three primary participants in the building of Expert System:
1. Expert: The success of an ES much depends on the knowledge provided by human experts. These experts
are those persons who are specialized in that specific domain.
2. Knowledge Engineer: Knowledge engineer is the person who gathers the knowledge from the domain
experts and then codifies that knowledge to the system according to the formalism.
3. End-User: This is a particular person or a group of people who may not be experts, and working on the
expert system needs the solution or advice for his queries, which are complex.
Why Expert System?
Before using any technology, we must have an idea about why to use that technology and hence the same for the
ES. Although we have human experts in every field, then what is the need to develop a computer-based system.
So below are the points that are describing the need of the ES:
1. No memory Limitations: It can store as much data as required and can memorize it at the time of its
application. But for human experts, there are some limitations to memorize all things at every time.
2. High Efficiency: If the knowledge base is updated with the correct knowledge, then it provides a highly
efficient output, which may not be possible for a human.
3. Expertise in a domain: There are lots of human experts in each domain, and they all have different skills,
different experiences, and different skills, so it is not easy to get a final output for the query. But if we put
the knowledge gained from human experts into the expert system, then it provides an efficient output by
mixing all the facts and knowledge
4. Not affected by emotions: These systems are not affected by human emotions such as fatigue, anger,
depression, anxiety, etc.. Hence the performance remains constant.
5. High security: These systems provide high security to resolve any query.
6. Considers all the facts: To respond to any query, it checks and considers all the available facts and provides
the result accordingly. But it is possible that a human expert may not consider some facts due to any
reason.
7. Regular updates improve the performance: If there is an issue in the result provided by the expert systems,
we can improve the performance of the system by updating the knowledge base.
Capabilities of the Expert System
Below are some capabilities of an Expert System:
o Advising: It is capable of advising the human being for the query of any domain from the particular ES.
o Provide decision-making capabilities: It provides the capability of decision making in any domain, such
as for making any financial decision, decisions in medical science, etc.
o Demonstrate a device: It is capable of demonstrating any new products such as its features, specifications,
how to use that product, etc.
o Problem-solving: It has problem-solving capabilities.
o Explaining a problem: It is also capable of providing a detailed description of an input problem.
o Interpreting the input: It is capable of interpreting the input given by the user.
o Predicting results: It can be used for the prediction of a result.
o Diagnosis: An ES designed for the medical field is capable of diagnosing a disease without using multiple
components as it already contains various inbuilt medical tools.
Advantages of Expert System
o These systems are highly reproducible.
o They can be used for risky places where the human presence is not safe.
o Error possibilities are less if the KB contains correct knowledge.
o The performance of these systems remains steady as it is not affected by emotions, tension, or fatigue.
o They provide a very high speed to respond to a particular query.
Limitations of Expert System
o The response of the expert system may get wrong if the knowledge base contains the wrong information.
o Like a human being, it cannot produce a creative output for different scenarios.
o Its maintenance and development costs are very high.
o Knowledge acquisition for designing is much difficult.
o For each domain, we require a specific ES, which is one of the big limitations.
o It cannot learn from itself and hence requires manual updates.
Applications of Expert System
o In designing and manufacturing domain
It can be broadly used for designing and manufacturing physical devices such as camera lenses and
automobiles.
o In the knowledge domain
These systems are primarily used for publishing the relevant knowledge to the users. The two popular
ES used for this domain is an advisor and a tax advisor.
o In the finance domain
In the finance industries, it is used to detect any type of possible fraud, suspicious activity, and advise
bankers that if they should provide loans for business or not.
o In the diagnosis and troubleshooting of devices
In medical diagnosis, the ES system is used, and it was the first area where these systems were used.
o Planning and Scheduling
The expert systems can also be used for planning and scheduling some particular tasks for achieving the
goal of that task.
Artificial Intelligence (AI) Technique
Artificial intelligence (AI) is both a tool and a fundamental shift in intelligence used by and for humans. What is
this paradigm composed of? Is it evolving well in all aspects of human intelligence? Let us explore.
Artificial intelligence (AI) is getting closer and closer to the heights and depths of human intelligence. That’s
what some of us want. That’s what we smell in John McCarthy’s words of AI’s description too. “The science and
engineering of making intelligent machines, especially intelligent computer programs.” And all this intelligence
comes from building agents that act rationally. That is where we can define the AI technique as a composite of
three areas. It is a type of method built on knowledge, which organizes and uses this knowledge and is also aware
of its complexity.
Let’s break this down one by one.
Search in artificial intelligence (AI)
Artificial intelligence (AI) agents essentially perform some kind of search algorithm in the background to
complete their expected tasks. That’s why search is a major building block for any artificial intelligence (AI)
solution.
Any artificial intelligence (AI) has a set of states, a start state from where the search begins, and a goal state. By
the use of search algorithms, the solution reaches from the start state to the goal state.
This is done through various approaches.
o Blind search
o Uninformed and informed search
o Depth first search
o Breadth first search
o Uniform cost search
o Search heuristics
Knowledge representation in artificial intelligence (AI)
Any artificial intelligence (AI) agent has to work on some input. This work can happen only when there is some
knowledge about the input or about its handling. Artificial intelligence (AI), hence, has to be strong in
understanding, reasoning, and interpreting knowledge. This is done by the representation of knowledge. It is
where the beliefs, intentions, and judgments of an intelligent agent are expressed by reasoning. This is the place
for modeling intelligent behavior for an agent.
Here, the representation of information from the real world happens for a computer to understand and leverage
this knowledge to solve complex real-life problems. This knowledge can be in the form of the following.
o Objects
o Events
o Performance
o Facts
o Meta-knowledge
 o Knowledge-base
o Declarative knowledge
o Structural knowledge
o Procedural knowledge
o Meta knowledge
o Heuristic knowledge
o Perception component
o Learning component
o Reasoning
o Execution component
All this is woven into many ways through logical, semantic, frame, and production rules- as ways of knowledge
representation.
Abstraction in artificial intelligence (AI)
When we talk of abstraction, we are looking at an arrangement of the complexity of computer systems. It helps
to reduce complexity and achieve a simplified view of various parts and their interplay with each other.
This is very important considering the significant criticism that AI tools face. The ‘black box’ effect is a big
problem because a lot of effective and stellar AI models cannot explain how they do what they do. This opacity
is a massive barrier to gaining confidence and adoption of artificial intelligence (AI). So several AI techniques
span these areas of search, knowledge, and abstraction. Like the following.
o Data Mining – where statistics and artificial intelligence are used for the analysis of large data sets to
discover helpful information
o Machine Vision – where the system can use imaging-based automatic inspection and analysis for
guidance, decisions, automatic inspection, process control, etc.
o Machine Learning (ML) – where models learn from experience and evolve their precision and delivery
over a period
o Natural Language Processing or NLP – where machines can understand and respond to text or voice
data
o Robotics – where expert systems can perform tasks like a human.
As we can see, these techniques are evolving and will keep getting better and sharper to bring artificial intelligence
(AI) into proximity to the complexity and beauty of human intelligence. We need a lot of work in these areas
because we need to address privacy, bias, discrimination, unexplainability, and misapplication that many artificial
intelligence (AI) solutions face. We can achieve more trust in AI and its techniques only by getting stronger in all
these areas – search, knowledge, and abstraction. That’s where we will remove the most significant gap between
a dog and a robot dog – a creature that human intelligence can feel sure of.