100103/CS700A

ARTIFICIAL
INTELLIGENCE
- MS. SANGEETHA JAMAL
- ASST. PROFESSOR
- DCS,RSET
Course Outcomes
After the completion of the course the student will be able to

Course Outcome 1 (CO1):Explain the fundamental concepts of intelligent

systems and their architecture.(Cognitive Knowledge Level: Understanding)
Course Outcome 2 (CO2): Illustrate uninformed and informed search
techniques for problem solving in intelligent systems. (Cognitive Knowledge
Level: Understanding )
Course Outcome 3 (CO3): Solve Constraint Satisfaction Problems using
search techniques. (Cognitive Knowledge Level: Apply )
Course Outcome 4 (CO4): Represent AI domain knowledge using logic
systems and use inference techniques for reasoning in intelligent systems.
(Cognitive Knowledge Level: Apply )
Course Outcome 5 (CO5): Illustrate different types of learning techniques
used in intelligent systems (Cognitive Knowledge Level: Understand)

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 2

Syllabus
Module 1: Introduction
Introduction – What is Artificial Intelligence (AI)? The Foundations of AI,
History of AI, Applications of AI. Intelligent Agents – Agents and
Environments, Good behavior: The concept of rationality, nature of
Environments, Structure of Agents.
Module 2: Problem Solving
Solving Problems by searching-Problem solving Agents, Example
problems, Searching for solutions, Uninformed search strategies, Informed
search strategies, Heuristic functions.
Module 3: Search in Complex environments
Adversarial search - Games, Optimal decisions in games, The Minimax
algorithm, Alpha-Beta pruning. Constraint Satisfaction Problems –
Defining CSP, Constraint Propagation- inference in CSPs, Backtracking
search for CSPs, Structure of CSP problems.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 3

Module 4: Knowledge Representation and Reasoning
Logical Agents – Knowledge based agents, Logic, Propositional Logic,
Propositional Theorem proving, Agents based on Propositional Logic. First Order
Predicate Logic – Syntax and Semantics of First Order Logic, Using First Order
Logic, Knowledge representation in First Order Logic. Inference in First Order
Logic – Propositional Vs First Order inference, Unification and Lifting, Forward
chaining, Backward chaining, Resolution.
Module 5: Machine Learning
Learning from Examples – Forms of Learning, Supervised Learning, Learning
Decision Trees, Regression and classification with Linear models, Introduction to
Generative AI.
Text Books
1. Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach,
3rd Edition. Prentice Hall.
2. D. Poole and A. Mackworth. Artificial Intelligence: Foundations of
Computational Agents, Cambridge University Press, 2010

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 4

Module I
What if computers
DON’T have
brains!!!
Bake the cake at 120 degrees!

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 7

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 8
Google Eyes- smart view glasses

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 9

"autonomous vehicle" project,
using a Toyota Prius

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 10

Human like Robots

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 11

Will future computers be such
small

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 12

Future Computers

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 13

Future Computers

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 14

AI Growth

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 15

 Introduction
AI is the Design of intelligence in an artificial device. The term was coined
by John McCarthy in 1956.
Intelligence is the ability to acquire, understand and apply the knowledge
to achieve goals in the world.
AI is unique, sharing borders with Mathematics, Computer Science,
Philosophy, Psychology, Biology, Cognitive Science and many others.
It can be described as an attempt to build machines that like humans can
think and act, able to learn and use knowledge to solve problems on their
own

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 16

Artificial Intelligence (AI) is a branch of Science which deals with helping
machines find solutions to complex problems in a more human-like
fashion.
Artificial Intelligence is concerned with the design of intelligence in an
artificial device.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 17

Alan Turing
Father of Modern Computing

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 18

Turing decoding machine

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 19

Foundations of
AI
Foundations of AI

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 21

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 22
 m lls can a
l e
b ski
o machine
pr ing think?
olv
s

xity
e
cal , pl ry, ogic
i m o l ,
t ist ling s co the ms, nce
g
sta ode uou ics, ir th fere min d
m ntin mat l go in m an g.
a nd gra es, in
co the a ro ag ild
m
a p gu bu
lan tem
s
sy

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 23

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 24
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 25
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 26
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 27
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 28
Applications of AI

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 29

History of AI
In 1931, Goedel layed the foundation of Theoretical Computer Science
1920-30s: He published the first universal formal language and showed
that math itself is either flawed or allows for unprovable but true
statements.
In 1936, Turing reformulated Goedel’s result and church’s extension
thereof.
In 1956, John McCarthy coined the term "Artificial Intelligence" as the
topic of the Dartmouth Conference, the first conference devoted to the
subject.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 30

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 31
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 32
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 33
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 34
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 35
History of AI….
In 1957, The General Problem Solver (GPS) demonstrated by Newell,
Shaw & Simon
In 1958, John McCarthy (MIT) invented the Lisp language.
In 1959, Arthur Samuel (IBM) wrote the first game-playing program, for
checkers, to achieve sufficient skill to challenge a world champion.
In 1963, Ivan Sutherland's MIT dissertation on Sketchpad introduced
the idea of interactive graphics into computing.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 36

History of AI….
In 1966, Ross Quillian (PhD dissertation, Carnegie Inst. of Technology;
now CMU) demonstrated semantic nets
In 1967, Dendral program (Edward Feigenbaum, Joshua Lederberg,
Bruce Buchanan, Georgia Sutherland at Stanford) demonstrated to
interpret mass spectra on organic chemical compounds. First successful
knowledge-based program for scientific reasoning.
In 1967, Douglas Engelbart invented the mouse at SRI

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 37

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 38
History of AI….
In 1968, Marvin Minsky & Seymour Papert publish Perceptrons,
demonstrating limits of simple neural nets.
In 1972, Prolog developed by Alain Colmerauer
In Mid 80’s, Neural Networks become widely used with the
Backpropagation algorithm (first described by Werbos in 1974).
1990, Major advances in all areas of AI, with significant demonstrations
in machine learning, intelligent tutoring, case-based reasoning,
multi-agent planning, scheduling, uncertain reasoning, data mining,
natural language understanding and translation, vision, virtual reality,
games, and other topics.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 39

History of AI….
In 1997, Deep Blue beats the World Chess Champion Kasparov
In 2002,iRobot, founded by researchers at the MIT Artificial Intelligence
Lab, introduced Roomba, a vacuum cleaning robot. By 2006, two million
had been sold.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 40

Definitions of AI

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 41

Definitions of AI

REASONING

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 42

Definitions of AI

REASONING

BEHAVIOUR

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 43

Definitions of AI

REASONING

HUMAN
PERFORMANCE

BEHAVIOUR

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 44

Definitions of AI

REASONING

HUMAN
PERFORMANCE RATIONALITY

BEHAVIOUR

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 45

INTELLIGENT SYSTEMS
To design intelligent systems-categorize them into four
categories (Luger and Stubberfield 1993), (Russell and Norvig,
2003)
1. Systems that think like humans
2. Systems that think rationally
3. Systems that behave like humans
4. Systems that behave rationally

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 46

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 47
 Approach 1: Acting Humanly
Turing test: ultimate test for acting humanly
◦ Computer and human both interrogated by judge
◦ Computer passes test if judge can’t tell the difference

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 48

 How effective is this test?
Agent must:
◦ Have command of language
◦ Have wide range of knowledge
◦ Demonstrate human traits (humor, emotion)
◦ Be able to reason
◦ Be able to learn

Loebner prize competition is modern version of Turing Test

◦ Example: Alice, Loebner prize winner for 2000 and 2001

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 49

 Chinese Room Argument
Imagine you are sitting in a room with a library of rule books, a bunch of blank exercise books,
and a lot of writing utensils. Your only contact with the external world is through two slots in
the wall labeled ``input'' and ``output''. Occasionally, pieces of paper with Chinese characters
come into your room through the ``input'' slot. Each time a piece of paper comes in through
the input slot your task is to find the section in the rule books that matches the pattern of
Chinese characters on the piece of paper. The rule book will tell you which pattern of
characters to inscribe the appropriate pattern on a blank piece of paper. Once you have
inscribed the appropriate pattern according to the rule book your task is simply to push it out
the output slot.

By the way, you don't understand Chinese, nor are you aware that the symbols that you are
manipulating are Chinese symbols.

In fact, the Chinese characters which you have been receiving as input have been questions
about a story and the output you have been producing has been the appropriate, perhaps
even "insightful," responses to the questions asked. Indeed, to the outside questioners your
output has been so good that they are convinced that whoever (or whatever) has been
producing the responses to their queries must be a native speaker of, or at least extremely
fluent in, Chinese.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 50

Do you understand Chinese?
Searle says NO
What do you think?
Is this a refutation of the possibility of AI?
The Systems Reply
◦ The individual is just part of the overall system, which does understand Chinese

The Robot Reply

◦ Put same capabilities in a robot along with perceiving, talking, etc. This agent would
seem to have genuine understanding and mental states.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 51

Approach 2: Thinking Humanly

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 52

 • Once we have a sufficiently precise theory of the mind, it becomes
possible to express the theory as a computer program.
• If the program’s input–output behavior matches corresponding
human behavior, that is evidence that it thinks humanly.
• Cognitive science brings together computer models from AI and
experimental techniques from psychology to construct precise and
testable theories of the human mind

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 53

Approach 3: Thinking Rationally
Laws of Thought approach

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 54

Approach 4: Acting Rationally

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 55

Components of an AI System
An agent perceives its environment
through sensors and acts on the
environment through actuators.

Human: sensors are eyes, ears,

actuators (effectors) are hands,
legs, mouth.

Robot: sensors are cameras, sonar,

lasers, ladar, bump, effectors are
grippers, manipulators, motors

The agent’s behavior is described by its

function that maps percept to action.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 56

Rationality
A rational agent does the right thing (what is this?)
A fixed performance measure evaluates the sequence of observed
action effects on the environment

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 57

 PEAS
Use PEAS to describe task
◦ Performance measure
◦ Environment
◦ Actuators
◦ Sensors

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 58

 PEAS
Use PEAS to describe task environment
◦ Performance measure
◦ Environment
◦ Actuators
◦ Sensors

Example: Taxi driver

◦ Performance measure: safe, fast, comfortable (maximize profits)
◦ Environment: roads, other traffic, pedestrians, customers
◦ Actuators: steering, accelerator, brake, signal, horn
◦ Sensors: cameras, sonar, speedometer, GPS, odometer, accelerometer, engine
sensors

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 59

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock

Chess without a
clock

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 60

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 61

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 62

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Fully observable vs. partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 63

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon

Fully observable vs. partially observable

Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 64

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
tic al c e
Fully observable vs. partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 65

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
tic al c e
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
tic al mic ous
Fully observable vs. partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 66

Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
tic al c e
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
tic al mic ous

Fully observable vs.Medical diagnosis

partially observable
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 67
Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
tic al c e
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
tic al mic ous
Medical diagnosis Partial Stochas Episodic Stati Continu Single
Fully observable vs. partially observable tic c ous
Deterministic vs. stochastic / strategic
Episodic vs. sequential
Static vs. dynamic
Discrete vs. continuous
Single agent vs. multiagent
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 68
 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs.
tic al c e
partially observable
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
Deterministic vs. tic al mic ous
stochastic / strategic
Medical diagnosis Partial Stochas Episodic Stati Continu Single
Episodic vs. sequential tic c ous
Static vs. dynamic Image analysis
Discrete vs. continuous
Single agent vs.
multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 69

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs. partially tic al c e
observable
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
Deterministic vs. stochastic / tic al mic ous
strategic Medical diagnosis Partial Stochas Episodic Stati Continu Single
tic c ous
Episodic vs. sequential
Image analysis Fully Determi Episodic Semi Discret Single
Static vs. dynamic
nistic e
Discrete vs. continuous
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 70

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs. tic al c e
partially observable Taxi driving Partial Stochas Sequenti Dyna Continu Multi
Deterministic vs. stochastic tic al mic ous
/ strategic Medical diagnosis Partial Stochas Episodic Stati Continu Single
tic c ous
Episodic vs. sequential
Image analysis Fully Determi Episodic Semi Discret Single
Static vs. dynamic nistic e
Discrete vs. continuous Robot part picking
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 71

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs. tic al c e
partially observable Taxi driving Partial Stochas Sequenti Dyna Continu Multi
Deterministic vs. tic al mic ous
stochastic / strategic Medical diagnosis Partial Stochas Episodic Stati Continu Single
tic c ous
Episodic vs. sequential
Image analysis Fully Determi Episodic Semi Discret Single
Static vs. dynamic nistic e
Discrete vs. continuous Robot part picking Fully Determi Episodic Semi Discret Single
nistic e
Single agent vs. multiagent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 72

 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs. tic al c e
partially observable Taxi driving Partial Stochas Sequenti Dyna Continu Multi
tic al mic ous
Deterministic vs. stochastic
Medical diagnosis Partial Stochas Episodic Stati Continu Single
/ strategic tic c ous
Episodic vs. sequential Image analysis Fully Determi Episodic Semi Discret Single
Static vs. dynamic nistic e

Discrete vs. continuous Robot part picking Fully Determi Episodic Semi Discret Single
nistic e
Single agent vs. multiagent Interactive English
8/16/2024
tutor Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 73
 Environment Examples
Environment Obser Determi Episodic Stati Discret Agents
vable nistic c e
Chess with a clock Fully Strategi Sequenti Semi Discret Multi
c al e
Chess without a Fully Strategi Sequenti Stati Discret Multi
clock c al c e
Poker Partial Strategi Sequenti Stati Discret Multi
c al c e
Backgammon Fully Stochas Sequenti Stati Discret Multi
Fully observable vs. tic al c e
partially observable
Taxi driving Partial Stochas Sequenti Dyna Continu Multi
Deterministic vs. tic al mic ous
stochastic / strategic Medical diagnosis Partial Stochas Episodic Stati Continu Single
tic c ous
Episodic vs. sequential
Static vs. dynamic Image analysis Fully Determi Episodic Semi Discret Single
nistic e
Discrete vs. continuous Robot part picking Fully Determi Episodic Semi Discret Single
Single agent vs. nistic e
multiagent Interactive English Partial Stochas Sequenti Dyna Discret Multi
8/16/2024
tutor Prepared by Ms. Sangeetha Jamal,RSET(Autonomy)
tic 2021 Batch al mic e 74
Agent Types
Types of agents (increasing in generality and ability to handle complex
environments)
◦ Simple reflex agents
◦ Reflex agents with state
◦ Goal-based agents
◦ Utility-based agents
◦ Learning agent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 75

Agents and Environments

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 76

Agent
An Agent is anything that can be viewed as perceiving its environment
through sensors and acting upon that environment through actuators.
 A human agent has eyes, ears, and other organs for sensors and
hands, legs, mouth, and other body parts for actuators.
◦ A robotic agent might have cameras and infrared range finders for sensors
and various motors for actuators.
◦ A software agent receives keystrokes, file contents, and network packets as
sensory inputs and acts on the environment by displaying on the screen,
writing files, and sending network packets.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 77

 Percept: We use the term percept to refer to the agent's perceptual
inputs at any given instant.
PerceptSequence: An agent's percept sequence is the complete history
of everything the agent has ever perceived.
Agent function: Mathematically speaking, we say that an agent's
behavior is described by the agent function that maps any given percept
sequence to an action.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 78

 Agent program :Internally, the agent function for an artificial agent will
be implemented by an agent program. It is important to keep these two
ideas distinct. The agent function is an abstract mathematical
description; the agent program is a concrete implementation, running
on the agent architecture.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 79

 Simple Reflex Agent
Use simple “if then” rules
Can be short sighted

SimpleReflexAgent(percept)
state = InterpretInput(percept)
rule = RuleMatch(state, rules)
action = RuleAction(rule)
Return action

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 80

 Example: Vacuum Agent

Performance?
◦ 1 point for each square cleaned in time T?
◦ #clean squares per time step - #moves per time step?
Environment: vacuum, dirt, multiple areas defined by square regions
Actions: left, right, suck, idle
Sensors: location and contents
◦ [A, dirty]

Rational is not omniscient

◦ Environment may be partially observable
Rational is not clairvoyant
◦ Environment may be stochastic
Thus Rational is not always successful
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 81
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 82
Reflex Vacuum Agent
If status=Dirty then return Suck
else if location=A then return Right
else if location=B then right Left

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 83

Tic-Tac-Toe Game

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 84

 The board used to play the Tic-Tac-Toe game consists of 9 cells laid out
in the form of a 3x3 matrix.
If there exists a track whose all three cells have been marked by the
same symbol, then the player to whom that symbol have been assigned
wins and the game terminates.
If there exist no track whose cells have been marked by the same
symbol when there is no more blank cell on the board then the game is
drawn

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 85

Strategy-1

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 86

Algorithm

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 87

 Procedure
1) Elements of vector:
◦ 0: Empty
◦ 1: X
◦ 2: O
◦ → the vector is a ternary number

2) Store inside the program a move-table (lookuptable):

a) Elements in the table: 19683 (3^9 )
b) Element = A vector which describes the most
suitable move from the current game-board

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 88

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 89
Advantages/Disadvantages
1. A lot of space to store the Move-Table.
2. A lot of work to specify all the entries in the Move-Table.
3. Difficult to extend

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 90

 Strategy -2
1) Use vector, called board, as Solution 1
2) However, elements of the vector:
◦ 2: Empty
◦ 3: X
◦ 5: O

3) Turn of move: indexed by integer 1,2,3, etc

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 91

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 92
 Advantages/Disadvantages
1. Not efficient in time, as it has to check several conditions before
making each move.
2. Easier to understand the program’s strategy.
3. Hard to generalize.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 93

Solving, General problem
solving
Problem solving is a process of generating solutions from observed data.
−a problem is characterized by a set of goals,
−a set of objects, and
−a set of operations.

These could be ill-defined and may evolve during problem solving.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 94

Searching Solutions:
To build a system to solve a problem:
1. Define the problem precisely
2. Analyze the problem
3. Isolate and represent the task knowledge that is necessary to solve
the problem
4. Choose the best problem-solving techniques and apply it to the
particular problem.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 95

Defining the problem as State
Space Search:
The state space representation forms the basis of most of the AI
methods.
◦ Formulate a problem as a state space search by showing the legal problem
states, the legal operators, and the initial and goal states.
◦ A state is defined by the specification of the values of all attributes of
interest in the world
◦ An operator changes one state into the other; it has a precondition which is
the value of certain attributes prior to the application of the operator, and a
set of effects, which are the attributes altered by the operator
◦ The initial state is where you start
◦ The goal state is the partial description of the solution

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 96

Rationality

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 97

Definition of a Rational Agent
“For each possible percept sequence, a rational agent should select an
action that is expected to maximize its performance measure, given the
evidence provided by the percept sequence and whatever built-in
knowledge the agent has.”

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 98

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 99
 agent-assumptions for
rationality
The performance measure awards one point for each clean square at each
time step, over a “lifetime” of 1000 time steps.
The “geography” of the environment is known a priori, but the dirt
distribution and the initial location of the agent are not. Clean squares stay
clean and sucking cleans the current square. The Left and Right actions
move the agent left and right except when this would take the agent
outside the environment, in which case the agent remains where it is.
The only available actions are Left, Right, and Suck.
The agent correctly perceives its location and whether that location
contains dirt

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 100

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 101
Omniscience, learning, and
autonomy
An omniscient agent knows the actual outcome of its actions and can
act accordingly; but omniscience is impossible in reality.
Example—
Rationality maximizes expected performance, while perfection
maximizes actual performance
Rationality does not require omniscience
Information Gathering
◦ Doing actions in order to modify future percepts is called as information
gathering

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 102

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 103
Structure of an agent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 104

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 105
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 106
Agent Types
Agents can be grouped into 5 classes based on their degree of
perceived intelligence and capability.
Types of agents (increasing in generality and ability to handle complex
environments)
◦ Simple reflex agents;
◦ Model-based reflex agents;
◦ Goal-based agents;
◦ Utility-based agents.
◦ Learning Agent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 107

Simple Reflex Agent

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 108

 Simple Reflex Agent
Use simple “if then” rules
Can be short sighted

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 109

CONDITION–ACTION RULE

if car-in-front-is-braking then initiate-braking.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 110

Model-based reflex agents

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 111

 Model-based reflex agents
Partial observability is for
the agent to keep track of
the part of the world it
can’t see now
Store
previously-observed
information
Can reason about
unobserved aspects of
current state

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 112

Changing lanes-the agent needs to keep track of where the other cars
are if it can’t see them all at once.
Updating the internal state information as time goes by requires two
kinds of knowledge to be encoded in the agent program.
◦ First, we need some information about how the world evolves independently
of the agent—for example, that an overtaking car generally will be closer
behind than it was a moment ago.
◦ Second, we need some information about how the agent’s own actions
affect the world—for example, that when the agent turns the steering wheel
clockwise, the car turns to the right, or that after driving for five minutes
northbound on the freeway, one is usually about five miles north of where
one was five minutes ago

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 113

“how the world works” —is called a model of the world. An agent that
uses such a model is called a model-based agent.

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 114

Goal-Based Agents

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 115

 Goal-Based Agents
Goal reflects desires of agents
May project actions to see if
consistent with goals
Takes time, world may change
during reasoning
Search & Planning also to be
included

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 116

Utility-Based Agents

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 117

 Utility-Based Agents
Evaluation function to measure
utility f(state) -> value
Useful for evaluating competing
goals

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 118

Learning Agents

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 119

Learning Agents

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 120

How Components of an agent
work?
“What is the world like now?”
“What action should I do now?”
“What do my actions do?”
“How on earth do these components work?”

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 121

Representation of states and
transitions
Represent along an axis of increasing complexity
and expressive power:
▪ atomic
▪ factored
▪ structured

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 122

Atomic Representation
Each state of the world is indivisible—it has no internal structure

A state (such as B or C) is
a black box with no
internal structure

Travelling from city A to city B

Reduce the state of world to just the name –like a city name
Algorithms like :
▪ Search and game-playing
▪ Hidden Markov models
▪ Markov decision processes

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 123

 Factored Representation
A factored representation splits up each state into a fixed set of variables or
attributes, each of which can have a value.

A state consists of a vector of

attribute values; values can be
Boolean, real valued, or one of a
fixed set of symbols

With factored representations, we can also represent uncertainty

▪ How much fuel in vehicle?
Algorithms like :
▪ Constraint satisfaction algorithms ▪ Propositional logic
▪ Bayesian networks
▪ Planning
▪ Machine learning algorithms

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 124

 Structured Representation
For many purposes, we need to understand the world as having things in it
that are related to each other, not just variables with values.

A state includes
objects, each of which
may have attributes of
its own as well as
relationships to other
objects.
(c)

Objects and their various and varying relationships can be described explicitly.
Structured representations underlie relational databases and first-order logic ,
first-order probability models , knowledge-based learning and much of natural
language understanding . In fact, almost everything that humans express in
natural language concerns objects and their relationships

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 125

PEAS Examples

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 126

Pathfinder Medical Diagnosis
System
Performance: Correct Hematopathology diagnosis
Environment: Automate human diagnosis, partially observable,
deterministic, episodic, static, continuous, single agent
Actuators: Output diagnoses and further test suggestions
Sensors: Input symptoms and test results
Reasoning: Bayesian networks, Monte-Carlo simulations

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 127

TDGammon
Performance: Ratio of wins to losses
Environment: Graphical output showing dice roll and piece movement,
fully observable, stochastic, sequential, static, discrete, multiagent
World Champion Backgammon Player
Sensors: Keyboard input
Actuator: Numbers representing moves of pieces
Reasoning: Reinforcement learning, neural networks

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 128

Alvinn
Performance: Stay in lane, on road, maintain speed
Environment: Driving Hummer on and off road without manual control
(Partially observable, stochastic, episodic, dynamic, continuous, single
agent), Autonomous automobile
Actuators: Speed, Steer
Sensors: Stereo camera input
Reasoning: Neural networks

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 129

 Talespin
Performance: Entertainment value of generated story
Environment: Generate text-based stories that are creative and understandable
◦ One day Joe Bear was hungry. He asked his friend Irving Bird where some honey was.
Irving told him there was a beehive in the oak tree. Joe threatened to hit Irving if he
didn't tell him where some honey was.
◦ Henry Squirrel was thirsty. He walked over to the river bank where his good friend Bill
Bird was sitting. Henry slipped and fell in the river. Gravity drowned. Joe Bear was hungry.
He asked Irving Bird where some honey was. Irving refused to tell him, so Joe offered to
bring him a worm if he'd tell him where some honey was. Irving agreed. But Joe didn't
know where any worms were, so he asked Irving, who refused to say. So Joe offered to
bring him a worm if he'd tell him where a worm was. Irving agreed. But Joe didn't know
where any worms were, so he asked Irving, who refused to say. So Joe offered to bring
him a worm if he'd tell him where a worm was…

Actuators: Add word/phrase, order parts of story

Sensors: Dictionary, Facts and relationships stored in
database
Reasoning: Planning
8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 130
Webcrawler Softbot
Search web for items of interest
Perception: Web pages
Reasoning: Pattern matching
Action: Select and traverse hyperlinks

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 131

Other Example AI Systems
Translation of Caterpillar truck Billiards robot
manuals into 20 languages
Juggling robot
Shuttle packing
Credit card fraud detection
Military planning (Desert Storm)
Lymphatic system diagnoses
Intelligent vehicle highway
negotiation Mars rover

Credit card transaction monitoring Sky survey galaxy data analysis

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 132

Other Example - AI Systems
Knowledge Representation Natural language processing
Search Uncertainty reasoning
Problem solving Computer Vision
Planning Robotics
Machine learning

8/16/2024 Prepared by Ms. Sangeetha Jamal,RSET(Autonomy) 2021 Batch 133

End of Module I