Books To Refer

1. Artificial Intelligence: A Modern Approach written by Stuart Russell &

Peter Norvig, Second Ed, Pearson
2. Artificial Intelligence written by Elaine Rich & Kevin Knight, Third Ed,
Tata McGraw Hill
3. Pattern Classification written by Richard Duda
4. Introduction to Artificial Intelligence written by E Charniak and D
McDermott, Pearson Education
5. Artificial Intelligence and Expert Systems written by Dan W. Patterson, ,
Prentice Hall of India
1
 Human vs Computer
1. Living device 1. Non-living device
2. Self-willed and creative 2. Dependent/programmed
3. Continuous nature 3. Discrete in nature
4. Limited memory size 4. Unlimited memory size
5. Neuron 5. RAM cell
6. Electro-chemical storage 6. Electronic and magnetic storage
7. Slow 7. Fast
8. Speed of transmission (50-100 m/s) 8. Approx. speed of light
9. Reasoning capability 9. No reasoning power
10. Has emotions 10. Dumb and no emotions
11. Learning capability 11. Must be programmed
12. Power consumption 10W 12. Approx. 500W
13. Fuzzy logic 13. Binary logic

2
 What is AI?
• Intelligence: “ability to learn, understand and think”

• AI is the study of how to make computers make

things which at the moment people do better.

• Examples: Speech recognition, Smell, Face, Object,

Intuition, Inferencing, Learning new skills, Decision
making, Abstract thinking

3
Allied Disciplines
AI
What is AI
 Acting Humanly: The Turing Test
• Alan Turing (1912-1954)
• “Computing Machinery and Intelligence”
(1950) Imitation Game
Huma
n

Human
AI
Interrogator
System
9
Foundation of AI
 The Foundations of AI
• Philosophy (423 BC  present):
• Can formal rules be used to draw valid
conclusions?
• How does the mental mind arise from a
physical brain?
• Where does knowledge come from?
• How does knowledge lead to action?
 Logic, methods of reasoning.
 Foundations of learning, language, and rationality.

12
 The Foundations of AI
• Mathematics (c.800  present):
• What are the formal rules to draw valid
conclusions?
• What can be computed?
• How do we reason with uncertain information?
 Formal representation and proof.
 Algorithms, computation, decidability, tractability.
 Probability.

13
 The Foundations of AI
• Economics (1776  present):
• How should we make decisions so as to maximize payoff?
• How should we do this when others may not go along?
• How should we do this when the payoff may be far in the future?
 Decision theory.
 Operation research.

• Neuroscience (1861  present):
• How do brains process information?
 Neurons.
 Synapses.

14
 The Foundations of AI
• Psychology (1879  present):
• How do humans and animals think and act?
 Adaptation.
 Phenomena of perception and motor control.
 Experimental techniques.

• Linguistics (1957  present):

• How does language relate to thought?
 Knowledge representation.
 Grammar.


15
 The Foundations of AI
• Computer engineering (1940  present):
• How can we build an efficient computer?
 intelligence and artifacts.


• Control theory and Cybernetics (1948 

present):
• How can artifacts operate under their own
control?
 Control theory.


16
 A Brief History of AI
• The gestation of AI (1943  1956):
 1943: McCulloch & Pitts: Boolean circuit model of brain.
 1950: Turing’s “Computing Machinery and Intelligence”.
 1956: McCarthy’s name “Artificial Intelligence” adopted.

• Early enthusiasm, great expectations (1952  1969):

– GPS
 Early successful AI programs: Samuel’s checkers,
Newell & Simon’s Logic Theorist, Gelernter’s Geometry
Theorem Prover.
 Robinson’s complete algorithm for logical reasoning.


17
 A Brief History of AI
• A dose of reality (1966  1974):
 AI discovered computational complexity.
 Neural network research almost disappeared after
Minsky & Papert’s book in 1969.

• Knowledge-based systems (1969  1979):

 1969: DENDRAL by Buchanan et al.(to study hypothesis
formation and discovery in science)
 1976: MYCIN by Shortliffle.(to identify bacteria causing severe
infections)
 1979: PROSPECTOR by Duda et al.( Evaluation of the mineral potential of a
geological site or region)



18
 A Brief History of AI
• AI becomes an industry (1980  1988):
 Expert systems industry booms.
 1981: Japan’s 10-year Fifth Generation project.

• The return of NNs and novel AI (1986 

present):
 Mid 80’s: Back-propagation learning algorithm reinvented.
 Expert systems industry busts.
 1988: Resurgence of probability.
 1988: Novel AI (ALife, GAs, Soft Computing, …).
 1995: Agents everywhere.
 2003: Human-level AI back on the agenda.

19
Intelligent Agents
 Agents
• An agent is anything that can be viewed as perceiving
its environment through sensors and acting upon that
environment through actuators.
Example:
• Human agent
– eyes, ears, and other organs for sensors;
– Hands, legs, mouth, and other body parts for actuators.
• Robotic agent:
– cameras and infrared range finders for sensors;
– various motors for actuators.
• Software agents???
Agents and Environments
 Agents and environments
• Percept: agent’s perceptual inputs at any given
instant.
• Percept sequence: the complete history of
everything the agent has ever perceived.
• The agent function maps from percept histories to
actions:
[f: P*  A]
• The agent program runs on the physical architecture
to produce f.
• agent = architecture + program
 Rational agents
• 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.
 Rational agents
• Rationality is distinct from omniscience (all-knowing
with infinite knowledge)
• Agents can perform actions in order to modify future
percepts so as to obtain useful information
(information gathering, exploration)
• An agent is autonomous if its behavior is determined
by its own experience (with ability to learn and
adapt)
PEAS
Task Environment Characterstics
 Simple reflex agents
• Simplest kind
• Select actions on the basis of the current percept, ignoring
the rest of the percept history.
• Condition-action rule
if car-in-front-is-braking then initiate-braking.
• Limited intelligence
• Works well if the environment is fully observable.
• Problem with partially observable environment. (vacuum
cleaner with dirt sensor only)
• Randomization for infinite loops (multiagent systems).
Simple reflex agents
Model-based reflex agents
 Goal-based agents

•
Utility-based agents
Learning agents
Computer Vision
 What is Computer Vision?
• Given an image or more, extract properties of
the 3D world
•Traffic scene
• Number of vehicles
• Type of vehicles
• Location of closest obstacle
• Assessment of congestion
• Location of the scene
captured
 Application of Computer Vision
• 123d Catch: Take your lot of Pictures and create 3-D Image
• Mercedes Benz/ Google Driverless car :use it to identify Pedestrian
• Virtual Dance /Games/
• Augmented reality( Pokémon)
• Autonomous cars
• Face recognition
• Gesture recognition
• Image search
• Machine vision
• Optical character recognition
• Robots
Vision and Computer Vision

37
 Computer Vision
• The computer vision problem can be stated as
follows:
Given a two-dimensional image, infer the
objects that produced it, including their shapes,
locations, colors and sizes.

38
 The Three Processing Levels
• Low-level processing
– Standard procedures are applied to improve image quality
– No “intelligent” capabilities

39
Biometrics

40
 Computer Vision involves:
• Image acquisition
• Image processing
• Image analysis
• Image understanding
Natural Language Processing
 NLP
• NLP Applications
• Information Retrieval – Information Extraction
– Question-Answering – Summarization –
Machine Translation – Dialogue Systems
 NLP
• The application of computational techniques to the analysis
and synthesis of natural language and speech.
• Natural-language processing (NLP) is a field of computer
science, artificial intelligence concerned with the interactions
between computers and human (natural) languages, and, in
particular, concerned with programming computers to
fruitfully process large natural language data.
• Challenges in natural-language processing frequently involve
speech recognition, natural-language understanding, and
natural-language generation.
 Introduction
NLP problem can be divided into two tasks:

• NLP may focus on language processing or generation.

– Language processing: Processing written text, using lexical,
syntactic and semantic knowledge of the language as well as the
required real world information.
– Generation. Processing spoken language, using all the information
needed above plus additional knowledge about phonology as well as
enough added information to handle the further ambiguities that arise
in speech.
 NLP
• NLP’s performed by solving a number of sub-
problems, where each sub-problem constitute a level
(mentioned earlier).
• Note that, a portion of those levels could be applied,
not necessarily all of them. For example some
applications require the first 3 levels only. Also, the
levels could be applied in a different order
independent of their granularity.
 Problems
• Ambiguity
– Multiple word meaning (flat)
– Syntactic ambiguity (I hit the man with the hammer)
– Unclear antecedents (John hit Bill because he sympathized with Mary)
• Imprecision
– (I have been waiting in the doctor’s room for a long time)
– (The crops died because it had not rain for a long time)
• Incompleteness
– (Ram had a cup of coffee and Shyam had tea)
• Inaccuracy
– (Spelling errors, improper punctuation)
Human Solutions
 Grammer
• P: S-> NP VP
NP->ART N
VP->V NP
N->boy|lollipop|frog
V->ate|kissed|flew
ART->the|a