0% found this document useful (0 votes)
270 views17 pages

Artificial Intelligence

The document discusses artificial intelligence and provides definitions, challenges, approaches, tools, and applications of AI. It defines AI as the study of intelligent agents that perceive their environment and take actions to achieve goals. Some key challenges discussed include reasoning and problem solving, knowledge representation, and perception. The document outlines various approaches to AI like symbolic, cognitive simulation, and statistical learning. Tools discussed include search and optimization, artificial neural networks, and ontologies. The document provides several examples of applications of AI in areas like healthcare, automotive, finance, and games.

Uploaded by

Balaji Moturu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
270 views17 pages

Artificial Intelligence

The document discusses artificial intelligence and provides definitions, challenges, approaches, tools, and applications of AI. It defines AI as the study of intelligent agents that perceive their environment and take actions to achieve goals. Some key challenges discussed include reasoning and problem solving, knowledge representation, and perception. The document outlines various approaches to AI like symbolic, cognitive simulation, and statistical learning. Tools discussed include search and optimization, artificial neural networks, and ontologies. The document provides several examples of applications of AI in areas like healthcare, automotive, finance, and games.

Uploaded by

Balaji Moturu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 17

Seminar

On
Artificial intelligence

presented by:
M.L.Sanghamithra
CONTENTS

INTRODUCTION
DEFINITION
CHALLENGES OF AI
APPROACHES
TOOLS
APPLICATIONS
REFERENCE
 INTRODUCTION

In computer science, artificial intelligence (AI), sometimes


called machine intelligence, is intelligence demonstrated
by machines, in contrast to the natural intelligence displayed
by humans. Leading AI textbooks define the field as the
study of “intelligent agents": any device that perceives its
environment and takes actions that maximize its chance of
successfully achieving its goals. Colloquially, the term
"artificial intelligence" is often used to describe machines that
mimic "cognitive" functions that humans associate with
the human mind, such as “learning" and "problem solving”.
REPRESENTATION OF ARTIFICIAL
INTELLIGENCE
 DEFINITION

Computer science defines AI research as the study of


"intelligent agents": any device that perceives its
environment and takes actions that maximize its chance
of successfully achieving its goals. A more elaborate
definition characterizes AI as “a system’s ability to
correctly interpret external data, to learn from such data,
and to use those learning's to achieve specific goals and
tasks through flexible adaptation.”
 CHALLENGES OF AI

• REASONING AND PROBLEM SOLVING:


Early researchers developed algorithms that imitated step-
by-step reasoning that humans use when they solve puzzles
or make logical deductions.[ By the late 1980s and 1990s, AI
research had developed methods for dealing
with uncertain or incomplete information, employing
concepts from probability and economics.
These algorithms proved to be insufficient for solving large
reasoning problems, because they experienced a
"combinatorial explosion": they became exponentially slower
as the problems grew larger. In fact, even humans rarely use
the step-by-step deduction that early AI research was able to
model. They solve most of their problems using fast, intuitive
judgments.
• KNOWLEDGE REPRESENTATION
Knowledge representation and knowledge engineering are
central to classical AI research. Some "expert systems"
attempt to gather together explicit knowledge possessed by
experts in some narrow domain. In addition, some projects
attempt to gather the "common-sense knowledge" known to
the average person into a database containing extensive
knowledge about the world. Among the things a
comprehensive common-sense knowledge base would contain
are: objects, properties, categories and relations between
objects; situations, events, states and time; causes and
effects; knowledge about knowledge (what we know about
what other people know); and many other, less well
researched domains. A representation of "what exists" is
an ontology: the set of objects, relations, concepts, and
properties formally described so that software agents can
interpret them.
An ontology represents knowledge as a set of
concepts within a domain and the relationships
between those concepts.
• PERCEPTION:

Machine perception is the ability to use input from sensors


(such as cameras (visible spectrum or infrared), microphones,
wireless signals, and active lieder, sonar, radar, and tactile
sensors to deduce aspects of the world. Applications
include speech recognition, facial recognition, and object
recognition. Computer vision is the ability to analyse visual
input. Such input is usually ambiguous; a giant, fifty-meter-tall
pedestrian far away may produce exactly the same pixels as a
nearby normal-sized pedestrian, requiring the AI to judge the
relative likelihood and reasonableness of different
interpretations, for example by using its "object model" to
assess that fifty-meter pedestrians do not exist.
 APPROACHE
S
There is no established unifying theory or paradigm that
guides AI research. Researchers disagree about many
issues. A few of the most long standing questions that
have remained unanswered are these: should artificial
intelligence simulate natural intelligence by
studying psychology or neurobiology? Or is human
biology as irrelevant to AI research as bird biology is
to aeronautical engineering? Can intelligent behaviour be
described using simple, elegant principles (such
as logic or optimization)? Or does it necessarily require
solving a large number of completely unrelated problems?
 VARIOUS APPROACHES OF AI ARE:

a. Cybernetics and Brain Simulation


b. Symbolic
c. Cognitive Simulation
d. Logic-based
e. Anti-Logic or Scruffy
f. Knowledge-based
g. Sub-Symbolic
h. Embodied Intelligence
i. Computational intelligence and soft computing
j. Statistical Learning
 TOOLS

• SEARCH AND OPTIMIZATION:


Many problems in AI can be solved in theory by
intelligently searching through many possible solutions:
Reasoning can be reduced to performing a search. For
example, logical proof can be viewed as searching for a
path that leads from premises to conclusions, where each
step is the application of an inference
rule Planning algorithms search through trees of goals
and sub-goals, attempting to find a path to a target goal, a
process called means-ends analysis. Robotics algorithms
for moving limbs and grasping objects use local
searches in configuration space. Many learning algorithms
use search algorithms based on optimization.
• ARTIFICIAL NEURAL NETWORKS:
Neural networks were inspired by the architecture of neurons in
the human brain. A simple "neuron" N accepts input from other
neurons, each of which, when activated (or "fired"), cast a
weighted "vote" for or against whether neuron N should itself
activate. Learning requires an algorithm to adjust these weights
based on the training data; one simple algorithm (dubbed "fire
together, wire together") is to increase the weight between two
connected neurons when the activation of one triggers the
successful activation of another. The neural network forms
"concepts" that are distributed among a sub-network of
shared neurons that tend to fire together; a concept meaning "leg"
might be coupled with a sub-network meaning "foot" that includes
the sound for "foot". Neurons have a continuous spectrum of
activation; in addition, neurons can process inputs in a nonlinear
way rather than weighing straightforward votes. Modern neural
networks can learn both continuous functions and, surprisingly,
digital logical operations.
A neural network is an interconnected group
of nodes, akin to the vast network
of neurons in the human brain.
 APPLICATIONS:

• AI is relevant to any intellectual task. Modern artificial


intelligence techniques are pervasive and are too numerous
to list here. Frequently, when a technique reaches
mainstream use, it is no longer considered artificial
intelligence; this phenomenon is described as the AI effect.

• High-profile examples of AI include autonomous vehicles


(such as drones and self-driving cars), medical diagnosis,
creating art (such as poetry), proving mathematical
theorems, playing games (such as Chess or Go), search
engines (such as Google search), online assistants (such
as Siri), image recognition in photographs, spam filtering,
predicting flight delays, prediction of judicial
decisions, targeting online advertisements, and energy
storage.
• AI CAN BE USED IN THE FOLLOWING
AREAS:
a. Health Care
b. Automotive
c. Finance and Economics
d. Government
e. Law related Professions
f. Video Games
g. Military
h. Audit
i. Advertising
j. Art
THE END

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy