vdocument.in_prof-saroj-kaushik1-introduction-to-artificial-intelligence-lecture-module.ppt

Prof Saroj Kaushik 1
Introduction to Artificial
Intelligence
Lecture Module 1

Contents
 Artificial Intelligence
 Characterstics of AI Program
 Categories of System
 Turing Test
 Foundations of AI
 Views of AI Goals
 Components of AI Programs
 Sub-areas of AI
 Applications
 Latest Perception of AI

Artificial Intelligence
 Quick Answer from Academia:
 Modeling human cognition or mental faculty
using computers
 Study of making computers do things which
at the moment people better
 Making computers do things which require
intelligence

More Formal Definition of AI
 AI is a branch of computer science which is
concerned with the study and creation of
computer systems that exhibit
 some form of intelligence
OR
 those characteristics which we associate
with intelligence in human behavior

 AI is a broad area consisting of
different fields, from machine vision,
expert systems to the creation of
machines that can "think".
 In order to classify machines as
"thinking", it is necessary to define
intelligence.

What is Intelligence?
 Intelligence is a property of mind that
encompasses many related mental abilities,
such as the capabilities to
 reason
 plan
 solve problems
 think abstractly
 comprehend ideas and language and
 learn

Characteristics of AI systems
 learn new concepts and tasks
 reason and draw useful conclusions about
the world around us
 remember complicated interrelated facts and draw
conclusions from them (inference)
 understand a natural language or perceive
and comprehend a visual scene
 look through cameras and see what's there
(vision), to move themselves and objects around
in the real world (robotics)

Contd..
 plan sequences of actions to complete a goal
 offer advice based on rules and situations
 may not necessarily imitate human senses and
thought processes
 but indeed, in performing some tasks differently, they
may actually exceed human abilities
 capable of performing intelligent tasks effectively
and efficiently
 perform tasks that require high levels of intelligence

Understanding of AI
 AI techniques and ideas seem to be
harder to understand than most things in
computer science
 AI shows best on complex problems for
which general principles don't help much,
though there are a few useful general
principles

 Artificial intelligence is also difficult to
understand by its content.
 Boundaries of AI are not well defined.
 Often it means the advanced software
engineering, sophisticated software
techniques for hard problems that can't be
solved in any easy way.
 AI programs - like people - are usually not
perfect, and even make mistakes.

 It often means, nonnumeric ways of
solving problems, since people can't
handle numbers well.
 Nonnumeric ways are generally "common
sense" ways, not necessarily the best
ones.
 Understanding of AI also requires an
understanding of related terms such as
intelligence, knowledge, reasoning,
thought, cognition, learning, and a number
of other computer related terms.

Categories of AI System
 Systems that think like humans
 Systems that act like humans
 Systems that think rationally
 Systems that act rationally

Systems that think like humans
 Most of the time it is a black box where we are
not clear about our thought process.
 One has to know functioning of brain and its
mechanism for possessing information.
 It is an area of cognitive science.
 The stimuli are converted into mental representation.
 Cognitive processes manipulate representation to build
new representations that are used to generate actions.
 Neural network is a computing model for
processing information similar to brain.

Systems that act like humans
 The overall behaviour of the system
should be human like.
 It could be achieved by observation.

Systems that think rationally
 Such systems rely on logic rather than human to
measure correctness.
 For thinking rationally or logically, logic formulas
and theories are used for synthesizing outcomes.
 For example,
 given John is a human and all humans are mortal then
one can conclude logically that John is mortal
 Not all intelligent behavior are mediated by logical
deliberation.

Systems that act rationally
 Rational behavior means doing right thing.
 Even if method is illogical, the observed
behavior must be rational.

The Turing Test
Turing proposed operational test for intelligent
behavior in 1950.
Human
Human ?
Interrogator
AI system

ELIZA
 Eliza was first program developed by Joseph
Wiezbaum to converse in English in mid
1960's
 It passed turing test.
 The following passage shows Eliza’s talking to
a teenage girl. Blue text Eliza’s response
Men are all alike.
IN WHAT WAY
They're always bugging us about something or other.
CAN YOU THINK OF A SPECIFIC EXAMPLE

Well, my boyfriend made me come here.
YOUR BOYFRIEND MADE YOU COME HERE
He says that I am depressed all the time.
I AM SORRY TO HEAR THAT YOU ARE DEPRESSED
It's true that I am unhappy
DO YOU THINK COMING HERE WILL HELP YOU NOT
TO BE UNHAPPY
I need help, that seems certain.
WHAT WOULD IT MEAN IF YOU GOT SOME HELP
Perhaps I could learn to get along with my mother.
TELL ME MORE ABOUT YOUR FAMILY

My mother takes care of me.
WHO ELSE IN YOUR FAMILY TAKES CARE OF YOU
My father.
YOUR FATHER
You are like my father in some ways.
WHAT RESEMBLANCE DO YOU SEE
You are not very aggressive but I think you don't want me to
notice that.
WHAT MAKES YOU THINK THAT I AM NOT VERY
AGGRESSIVE

You don’t argue with me.
WHY DO YOU THINK I DON’T ARGUE WITH YOU
You are afraid of me.
DOES IT PLEASE YOU TO BELIEVE, I AM AFRAID OF
YOU
My father is afraid of everybody.
WHAT ELSE COMES TO MIND WHEN YOU THINK OF
YOUR FATHER
Bullies.
DOES THAT HAVE ANYTHING TO DO WITH THE FACT
THAT YOUR BOYFRIEND MADE YOU COME HERE

Foundations of AI
 Foundation of AI is based on
 Mathematics
 Neuroscience
 Control Theory
 Linguistics

Foundations - Mathematics
 More formal logical methods
 Boolean logic
 Fuzzy logic
 Uncertainty
 The basis for most modern approaches to
handle uncertainty in AI applications can
be handled by
 Probability theory
 Modal and Temporal logics

Foundations - Neuroscience
 How do the brain works?
 Early studies (1824) relied on injured and
abnormal people to understand what parts of brain
work
 More recent studies use accurate sensors to
correlate brain activity to human thought
 By monitoring individual neurons, monkeys can now
control a computer mouse using thought alone
 Moore’s law states that computers will have as
many gates as humans have neurons in 2020
 How close are we to have a mechanical brain?
 Parallel computation, remapping, interconnections,….

Foundations – Control Theory
 Machines can modify their behavior in response
to the environment (sense/action loop)
 Water-flow regulator, steam engine governor,
thermostat
 The theory of stable feedback systems (1894)
 Build systems that transition from initial
state to goal state with minimum energy
 In 1950, control theory could only describe
linear systems and AI largely rose as a
response to this shortcoming

Foundations - Linguistics
 Speech demonstrates so much of human
intelligence
 Analysis of human language reveals thought
taking place in ways not understood in other
settings
 Children can create sentences they have never heard
before
 Language and thought are believed to be tightly
intertwined

Two Views of AI Goals
 AI is about duplicating what the (human)
brain DOES
 Cognitive Science
 AI is about duplicating what the (human)
brain SHOULD do
 Rationality (doing things logically)

Cool Stuff in AI
 Game playing agents
 Machine learning
 Speech
 Language
 Vision
 Data Mining
 Web agents …….

Useful Stuff
 Medical Diagnosis
 Fraud Detection
 Object Identification
 Space Shuttle Scheduling
 Information Retrieval ….

AI Techniques
 Rule-based
 Fuzzy Logic
 Neural Networks
 Genetic Algorithms

Components of AI Program
 AI techniques must be independent of
the problem domain as far as possible.
 AI program should have
 knowledge base
 navigational capability
 inferencing

Knowledge Base
 AI programs should be learning in nature
and update its knowledge accordingly.
 Knowledge base consists of facts and
rules.
 Characteristics of Knowledge:
 It is voluminous in nature and requires
proper structuring
 It may be incomplete and imprecise
 It may keep on changing (dynamic)

Navigational Capability
 Navigational capability contains
various control strategies
 Control Strategy
 determines the rule to be applied
 some heuristics (thump rule) may be
applied

Inferencing
 Inferencing requires
 search through knowledge base
and
 derive new knowledge

Sub-areas of AI
 Sub areas of AI are:
 Knowledge representation
 Theorem proving
 Game playing
 Vommon sense reasoning dealing with uncertainty
and decision making
 Learning models, inference techniques, pattern
recognition, search and matching etc.
 Logic (fuzzy, temporal, modal) in AI
 Planning and scheduling

Sub-areas of AI – Contd..
 Natural language understanding
 Computer vision
 Understanding spoken utterances
 Intelligent tutoring systems
 Robotics
 Machine translation systems
 Expert problem solving
 Neural Networks, AI tools etc

Applications
 Some of the applications are given below:
 Business : Financial strategies, give advice
 Engineering: check design, offer suggestions to
create new product
 Manufacturing: Assembly, inspection & maintenance
 Mining: used when conditions are dangerous
 Hospital : monitoring, diagnosing & prescribing
 Education : In teaching
 household : Advice on cooking, shopping etc.
 farming : prune trees & selectively harvest mixed
crops.

Latest Perception of AI
 Three typical components of AI Systems
THE WORLD
Perception Action
Reasoning

Recent AI
 Heavy use of
 probability theory
 decision theory
 statistics
 logic (fuzzy, modal, temporal)

vdocument.in_prof-saroj-kaushik1-introduction-to-artificial-intelligence-lecture-module.ppt

More Related Content

What's hot (20)

Similar to vdocument.in_prof-saroj-kaushik1-introduction-to-artificial-intelligence-lecture-module.ppt (20)

Recently uploaded (20)

vdocument.in_prof-saroj-kaushik1-introduction-to-artificial-intelligence-lecture-module.ppt