AGENDA

Introduction to AI
Introduction to ML and DL
ML and DL algorithm using python (applications)
Case study/project
S. Chapter Name Course Outline Duratio Learning Outcome
No n
(Hours)
Theory Lab
1 Introduction of 1.1 What is artificial 3 0 After completion of this
Artificial intelligence? module, the candidate
Intelligence (AI) 1.2 Basics concept of will be able to :
- Artificial Intelligence • Understand the
1.3 How do AI algorithms
concept of
work?
1.4 Types of AI algorithms AI and use of Python in
1.5 Uses of AI algorithms AI
1.6 AI algorithms and business

1
 Introduction to Artificial intelligence (AI):
a complete overview
In this age of rapid technological advancement, most people are familiar with AI. We’ve
likely all read the articles about automation destroying jobs, or a future of robots taking over
the world. While those articles are more based on science fiction than a tangible future of AI,
it certainly keeps interest in AI top-of-mind for many people.

There are dozens of examples of AI that everyday consumers may use, such as facial
recognition, auto-correct, search engines, or social media algorithms. But have you ever
wondered how these programs work?

AI runs off of algorithms, but not all AI algorithms are the same. They’re developed with
different goals and methods. In this course, we’ll talk about the four major categories of AI
algorithms and how they all work.

In this course, we’ll cover:

1. What is artificial intelligence?

2. Basics concept of Artificial Intelligence
3. How do AI algorithms work?
4. Types of AI algorithms
1. Supervised learning
2. Unsupervised learning
3. Both supervised and unsupervised learning
4. Reinforcement learning
5. Uses of AI algorithms
6. AI algorithms and business

1. What is artificial intelligence?

Artificial intelligence is a branch of computer science concerned with creating machines that
can think and make decisions independently of human intervention. Those AI programs can
do complex tasks that were previously only able to be done by humans. Some AI programs

2
can complete simple tasks, some more complex. Some can take in data to learn and improve,
completely without the touch of a human developer.

1.1 Examples and applications of AI

3
So what are some examples of AI? Well, it can be almost anything. Your smartphone uses AI,
as do services like digital assistants, chatbots, social media websites, and much more. Many
home electronics also use AI, such as robot vacuum cleaners or security systems. And, of
course, there are classic examples of auto-navigation and robotics.

Below, we’ve outlined applications in greater detail so you can understand how AI impacts
everyday life.

a) Digital assistants

Perhaps the application used by most people would be the digital assistants on our various
pieces of technology. If you have a smartphone or laptop, you probably have and use digital
assistant software to some degree.

Some of the most popular digital assistants include:

• Siri (Apple)
• Alexa (Amazon)
• Cortana (Microsoft)
• Google Assistant (Google)
• Bixby (Samsung)

4
b) Search engines

Another common application of AI is search engines. Search engine algorithms utilize AI to

refine and show better results without the intervention of programmers. You can see this in
action on Google if you search a question. You’ll see a section called “People also ask” and if
you open one of those questions, it will spawn two more related questions below.

An even simpler example is Google’s auto-complete answers when you type in the search bar.
An AI algorithm gathers data on what people search most often and uses that to populate
predictions you can use to navigate.

Popular search engines include:

• Google
• Yahoo
• Bing
• DuckDuckGo
c) Social media

Social media platforms are another common way people interact with AI. All major social
media platforms run off AI-powered algorithms which are designed to serve specific
purposes. Most use algorithms to determine what their users like and serve more of that
content, to keep the user engaged. Many also run AI algorithms to gather and store user data
to use for advertising purposes.

You can train your social media algorithms to show the content you like by creating filters, or
searching carefully for what you like, and purposefully interacting (liking, commenting,
sharing, etc.) with things you enjoy.

Popular social media platforms include:

• Facebook (Meta)
• Instagram (Meta)
• YouTube
• TikTok
d) Online shopping

This is probably one of the least obvious ways people interact with AI in their daily lives.
Many online shopping and ecommerce platforms use AI to streamline their customer
experience in a variety of ways.

As a customer, you may experience AI through:

• Personalized product recommendations based on previous shopping activity or

customer profile.

5
 • Pricing optimization based on supply, demand, or previous shopping activity.
• Chatbots to provide instant responses to customer service or technical issues.
• Shipping and delay estimates.

As a business owner, you may consider implementing AI in the following additional ways:

• Sales and demand forecasting to help you manage your inventory in the face of
increased or decreased demand.
• Creating customer profiles and segmentation to boost sales.
• Smart analytics to show in real-time how your business is performing.
e) Robots

The word “robot” probably makes many people think of sci-fi movies like Star Wars or shows
like Star Trek with their humanoid, intelligent robots. Though those may seem futuristic or
even far-fetched, in reality, many robots already exist in our world. You may even own some,
or something produced by one.

Robots are used in a myriad of fields to streamline production or keep workers safe. They
handle repetitive tasks or anything deemed too dangerous for a human worker. Some
examples of industrial robots include:

• Aerospace: You may be familiar with the Mars rovers NASA has landed over the
years. These are programmed to explore, gather samples and send transmissions back
to Earth to provide data from Mars that an astronaut would be unable to obtain. Most
recently, NASA sent the rover Perseverance to Mars to gather samples and search for
signs of ancient life.
• Manufacturing: The use of robots in assembly lines dates back to 1961, when
General Motors introduced a robot to assist with welding and transporting die casings
(jobs deemed too dangerous for humans). It continues to this day, streamlining
production and providing safer working conditions for humans.
• Hospitality: Particularly in recent years, the hospitality industry has adopted robots to
help complete simple tasks and fill in for worker shortages. These can do things like
check-in guests at hotels, mix drinks at cafes, deliver meals to tables in restaurants,
and more.

f) Transportation and Navigation

You’ve probably heard of self-driving cars, whether in a sci-fi show or in the news from
recent attempts by various companies. But there are more ways that AI is utilized in
transportation. Most major map software uses some kind of AI to interpret real-time traffic
data and provide routes and ETAs. Additionally, many aircraft use an AI-powered autopilot
that takes in weather conditions and flight data to set the course.

6
In fact, studies show that the application of AI in transportation has made it safer, more
efficient, and more reliable.

Other examples of AI in transportation and navigation include:

• Traffic management systems take in real-time data about the road, weather, and
traffic conditions to predict heavier traffic flows and congestion.
• Direction apps such as Google Maps, Apple Maps, and Waze all use location data
collected from users to determine traffic, ETAs, and more.
• Rideshare apps, much like direction apps, use AI that takes in location and
environmental data to give ETAs, predict road conditions, and set fare rates.
g) Text editing and autocorrect

Another example of AI in the palm of your hand (if you have a smartphone, anyway) is
autocorrect and other text editing software. This software takes input from generalized
dictionaries and common use but also learns from your specific patterns to pick up the words
you use most frequently and help you spell them.

Other online text editors like Grammarly or Hemingway App take standards of style, length,
and grammar, and compare them to your texts, generating reports on errors and readability
stats. Some of them also analyze other online content in real-time to compare for originality.

h) Fraud prevention

If you have an account with any major bank, chances are they use AI in their fraud detection
and prevention systems. These work by analyzing thousands of transactions, and recognizing
normal patterns so they can flag suspicious activity. These programs can auto-decline
anything suspicious and flag an investigation, as well as notify the individual for verification.

g) Predictions

Since AI can process large amounts of data all at once, it’s useful in identifying patterns and
using those to make predictions. Businesses can then use these predictions to make informed
decisions or prevent possible future issues.

Common uses of predictive AI include:

• Maintenance: Tracking previous repairs and general wear and tear on parts in
equipment allows AI to predict when maintenance needs to happen, preventing
inconvenient breakdowns or possible accidents.
• Modeling: Predictive modeling uses data mining and probability forecasting to predict
and estimate future outcomes.
i) Gaming

Perhaps surprisingly, AI has been in the field of gaming for years. Over the years, many AI
systems were designed to play various games as the developers worked on building software

7
that would learn. AIs have beaten human champions in Chess, Go, StarCraft 2, and also on
the game show Jeopardy.

Of course, many games also utilize AI in their development to continually increase interest
and incentives for users to keep playing. Some games that use AI include:

• Minecraft: uses AI to generate unending virtual environments and adapt to the

player’s style.
• F.E.A.R: uses enemy AI to allow characters to learn and adapt to the player’s
movements in game.
• The Last of Us: has a dynamic AI for each non-player character allowing them to
react differently to the player character depending on their specific choices.
j) Healthcare

From robotics in hospitals and clinics to predictive software used to diagnose rare diseases, AI
has many uses in the field of healthcare. Doctors and medical staff work with AI-powered
software to provide better care to patients of all types.

Some uses of AI in healthcare:

• Early diagnosis: AI can analyze patient and disease data to predict the likelihood of a
patient developing a disease and either diagnose it early or help to prevent it entirely.
• Disease tracking: Using predictive analytics, AI can model how a contagious disease
could spread over the course of time or across a specific area.
• Drug discovery: AI models can discover new applications or potentially harmful
interactions between different drugs.
k) Advertising

Like many of the above examples, AI has numerous applications in the field of advertising.
From offering dynamic ads based on demographics or location to AI that can write the copy
itself, AI drives the field of advertising and marketing forward.

Examples of AI in advertising:

• Ad creation: AI software can be trained to write copy or even make images based on
interaction and purchase data.
• Dynamic presentation: Many ad platforms allow you to create ads that present
different images or text based on customer demographics or location, personalizing
the ad experience.
• Budget optimization: Some ad platforms use AI to help determine where an
advertiser’s budget goes, focusing budget spending on the best-performing ad on the
most cost-effective days and times it to the best-performing ad, day, and time.
k) Analytics

8
Finally, another common use for AI is in the field of data science and analytics. One of the
most common uses is in predictive analytics, but AI can also be useful in data analysis. Most
crucially, using AI analytics helps companies to scale their analytics and allows them to have
accurate data at a much quicker rate than before.

Some common uses for AI in analytics are:

• Forecasting: Taking in historical data and creating a reasonable forecast of what you
can expect to see in the future.
• Predictive analytics: Predicting trends and future results based on historical data.
• Business monitoring: Real-time analytics on all key data points, from revenue to cost
to customer experience.

1.2 Business and AI

While that list of examples may seem extensive, it’s certainly not all-encompassing. There are
hundreds, if not thousands, of other ways AI touches everyday life for consumers.

For businesses, the application possibilities of AI may seem overwhelming. But it’s important
to consider how to adopt AI to grow your business, or risk being left behind as the technology
evolves. One easy way to do so is with AI analytics. Learn more about how Tableau helps our
customers succeed with AI analytics today.

9
2. What is an AI algorithm?
So then what is an AI algorithm? The definition of an algorithm is “a set of instructions to be
followed in calculations or other operations.” This applies to both mathematics and computer
science. So, at the essential level, an AI algorithm is the programming that tells the computer
how to learn to operate on its own.

An AI algorithm is much more complex than what most people learn about in algebra, of
course. A complex set of rules drive AI programs, determining their steps and their ability to
learn. Without an algorithm, AI wouldn’t exist.

3. How do AI algorithms work?

While a general algorithm can be simple, AI algorithms are by nature more complex. AI
algorithms work by taking in training data that helps the algorithm to learn. How that data is
acquired and is labeled marks the key difference between different types of AI algorithms.

At the core level, an AI algorithm takes in training data (labeled or unlabeled, supplied by
developers, or acquired by the program itself) and uses that information to learn and grow.
Then it completes its tasks, using the training data as a basis. Some types of AI algorithms can
be taught to learn on their own and take in new data to change and refine their process. Others
will need the intervention of a programmer in order to streamline.

4. Types of artificial intelligence algorithms

There are three major categories of AI algorithms: supervised learning, unsupervised learning,
and reinforcement learning. The key differences between these algorithms are in how they’re
trained, and how they function.

10
Under those categories, there are dozens of different algorithms. We’ll be talking about the
most popular and commonly used from each category, as well as where they are commonly
used.

4.1 Supervised learning algorithms

The first, and most commonly used category of algorithms is “Supervised learning.” These
work by taking in clearly-labeled data while being trained and using that to learn and grow. It
uses the labeled data to predict outcomes for other data. The name “supervised learning”
comes from the comparison of a student learning in the presence of a teacher or expert.

Building a supervised learning algorithm that actually works takes a team of dedicated experts
to evaluate and review the results, not to mention data scientists to test the models the
algorithm creates to ensure their accuracy against the original data, and catch any errors from
the AI.

11
a) Definitions: Classification and Regression

Below, we jump into explaining the different types of supervised learning algorithms. All of
them can either be used for classification or regression, or both.

Classification means an either/or result using binary (0 = no, 1 = yes). So the algorithm will
classify something as either one or another, but never both. There is also multi-class
classification, which deals with organizing data into defined categories or types relevant to a
specific need.

Regression means the result will end with a real number (either round or a decimal point).
You usually have a dependent variable and an independent variable, and the algorithm will
use both points to estimate a possible other result (either forecast or generalized estimate).

b) Decision Tree

One of the most common supervised learning algorithms, decision trees get their name
because of their tree-like structure (even though the tree is inverted). The “roots” of the tree
are the training datasets and they lead to specific nodes which denote a test attribute. Nodes
often lead to other nodes, and a node that doesn’t lead onward is called a “leaf”.

Decision trees classify all the data into decision nodes. It uses a selection criteria called
Attribute Selection Measures (ASM) which takes into account various measures (some
examples would be entropy, gain ratio, information gain, etc). Using the root data and
following the ASM, the decision tree can classify the data it is given by following the training
data into sub-nodes until it reaches the conclusion.

12
c) Random Forest

The random forest algorithm is actually a broad collection of different decision trees, leading
to its name. The random forest builds different decision trees and connects them to gain more
accurate results. These can be used for both classification and regression.

d) Support Vector Machines

The support vector machine (SVM) algorithm is another common AI algorithm that can be
used for either classification or regression (but is most often used for classification). SVM
works by plotting each piece of data on a chart (in N dimensional space where N = the
number of datapoints). Then, the algorithm classifies the datapoints by finding the hyperplace
that separates each class. There can be more than one hyperplane.

d) Naive Bayes

The reason this algorithm is called “Naive Bayes” is that it’s based on Bayes’ Theorem, and
also relies heavily on a large assumption: that the presence of one particular feature is
unrelated to the presence of other features in the same class. That major assumption is the
“naive” aspect of the name.

Naive Bayes is useful for large datasets with many different classes. It, like many other
supervised learning algorithms, is a classification algorithm.

13
f) Linear regression

Linear regression is a supervised learning AI algorithm used for regression modeling. It’s
mostly used for discovering the relationship between data points, predictions, and forecasting.
Much like SVM, it works by plotting pieces of data on a chart with the X-axis is the
independent variable and the Y-axis is the dependent variable. The data points are then plotted
out in a linear fashion to determine their relationship and forecast possible future data.

14
g) Logistic regression

A logistic regression algorithm usually uses a binary value (0/1) to estimate values from a set
of independent variables. The output of logistic regression is either 1 or 0, yes or no. An
example of this would be a spam filter in email. The filter uses logistic regression to mark
whether an incoming email is spam (0) or not (1).

Logistic regression is only useful when the dependent variable is categorical, either yes or no.

4.2 Unsupervised learning algorithms

It may at this point be relatively easy to guess what unsupervised learning algorithms mean, in
comparison to supervised learning. Unsupervised learning algorithms are given data that isn’t
labeled. Unsupervised learning algorithms use that unlabeled data to create models and
evaluate the relationships between different data points in order to give more insight to the
data.

15
a) Definition: Clustering

Many unsupervised learning algorithms perform the function of clustering, which means they
sort the unlabeled data points into pre-defined clusters. The goal is to have each data point
belong to only one cluster, with no overlap. There can be more than one data point in any
given cluster, but a data point cannot belong to more than one cluster.

b) K-means clustering

K-means is an algorithm designed to perform the clustering function in unsupervised learning.

It does this by taking in the pre-determined clusters and plotting out all the data regardless of
the cluster. It then plots a randomly-selected piece of data as the centroid for each cluster
(think of it as a circle around each cluster, with that piece of data as the exact center point).
From there, it sorts the remaining data points into clusters based on their proximity to each
other and the centroid data point for each cluster.

c) Gaussian mixture model

Gaussian mixture models are similar to K-means clustering in many ways. Both are
concerned with sorting data into pre-determined clusters based on proximity. However,
Gaussian models are a little more versatile in the shapes of the clusters they allow.

Picture a graph with all your data points plotted out. K-means clustering only allows data to
be clustered in circles with the centroid in the center of each cluster. Gaussian mixture can
handle data that lands on the graph in more linear patterns, allowing for oblong-shaped
clusters. This allows for greater clarity in clustering if one datapoint lands inside the circle of
another cluster.

4.3 Both supervised and unsupervised algorithms

Some AI algorithms can use either supervised or unsupervised data input and still function.
They might have slightly different applications based on their status.

a) K-nearest neighbor algorithm

16
K-nearest neighbor (KNN) algorithm is a simplistic AI algorithm that assumes that all the
data points provided are in proximity to each other and plots them out on a map to show the
relationship between them. Then the algorithm can calculate the distance between data points
in order to extrapolate their relationship, and calculate the distance on a graph.

In supervised learning, it can be used for either classification or regression applications. In

unsupervised learning, it’s popularly used for anomaly detection; that is, finding data that
doesn’t belong and removing it.

b) Neural Networks

Neural network algorithm is a term for a collection of AI algorithms that mimic the functions
of a human brain. These tend to be more complex than many of the algorithms discussed
above and have applications beyond some of the ones discussed here. In unsupervised and
supervised learning, it can be used for classification and pattern recognition.

4.4 Reinforcement learning algorithms

17
The last major type of AI algorithm is reinforcement learning algorithms, which learn by
taking in feedback from the result of its action. This is typically in the form of a “reward.

A reinforcement algorithm is usually composed of two major parts: an agent that performs an
action, and the environment in which the action is performed. The cycle begins when the
environment sends a “state” signal to the agent. That queues the agent to perform a specific
action within the environment. Once the action is performed, the environment sends a
“reward” signal to the agent, informing it on what happened, so the agent can update and
evaluate its last action. Then, with that new information, it can take the action again. That
cycle repeats until the environment sends a termination signal.

There are two types of reinforcement the algorithm can use: either a positive reward, or a
negative one.

a) Definitions: Model, Policy, Value

In reinforcement algorithms, there are slightly different approaches depending on what is

being measured and how it’s being measured. Here are some definitions of different models
and measures:

• Policy: The approach the agent takes to determine the next action taken by the agent.
• Model: The situation and dynamics of the environment.
• Value: The expected long-term results. This is different from the reward, which is the
result of a single action within the environment. The Value is the long-term result of
many actions.
b) Value-based

In a value-based reinforcement algorithm the agent pushes toward an expected long-term

return, instead of just focusing on the short-term reward.

c) Policy-based

18
A policy-based reinforcement algorithm usually takes one of two approaches to determining
the next course of action. Either a standardized approach where any state produces the same
action or a dynamic approach where certain probabilities are mapped out and probabilities
calculated. Each probability has its own policy reaction.

d) Model-based

In this algorithm, the programmer creates a different dynamic for each environment. That
way, when the agent is put into each different model, it learns to perform consistently under
each condition.

5 Uses of AI algorithms
There are thousands of applications for AI systems and algorithms. We touched on what may
seem like simple algorithms in this course , but even those have hundreds of possible
applications. The possibilities are endless.

Some common uses of AI algorithms include:

• Data entry and classification

• Advanced or predictive analytics
• Search engines (Google, Yahoo, Bing, etc.)
• Digital assistants (Siri, Alexa, etc.)
• Robotics (assembly machines, self-driving cars, etc.)

19
6 AI algorithms and business applications
Now that you know about the different ways AI works and a little about the possible
applications, it’s time to think about how you can use it in business. According to the 2021
Appen State of AI report, businesses need to adopt AI into their models or risk being left
behind as the technology advances.

Tableau knows how important it is for businesses to stay on the cutting edge of analytics to
ensure they can make the best steps forward at any given time. That’s why we developed AI
analytics, to offer the best predictive analytics to our clients. Learn how Tableau helps
customers succeed with AI analytics now.

20
21