Ch 1 – Introduction to AI

1
 Primary Book:
 Artificial Intelligence: A Modern Approach (AIMA)
 Authors: Stuart Russell and Peter Norvig (3rd Ed.)

 Reference Books:
1. Artificial Intelligence: A Guide To Intelligent
Systems (Second Edition) by Michael Negnevitsky
2. Agent Technology for Communication
Infrastructures by Alex L. G. Hayzelden and Rachel
A. Bourne.

2
 Introduction
 Approaches to AI
 The Foundation of AI
 Bits of history of AI
 The state of the art of AI

3
 AI Definitions
 “A branch of computer science that is concerned
with the automation of intelligent
behavior”(Luger & Stubblefield, 1993)
 “The design and study of computer programs
that behave intelligently. These programs are
constructed to perform as would a human or an
animal whose behavior we consider
intelligent”(Dean et al., 1995)
 “A field of study that seeks to explain and
emulate intelligent behavior in terms of
computational processes” (Schalkoff, 1990)
4
5
 The exciting new effort to make computers thinks
… machine with minds, in the full and literal sense”
(Haugeland 1985)
 The automation of activities that we associate with
human thinking, activities such as decision-making,
problem solving, learning,…(Bellman, 1978)

Think Like
Humans

6
 “The art of creating machines that perform functions
that require intelligence when performed by people”
(Kurzweil, 1990)
 “The study of how to make computers do things at
which, at the moment, people do better”, (Rich and
Knight, 1991)

Act Like
Humans

7
 “The study of mental faculties through the use of
computational models”,(Charniak et al. 1985)
 “The study of the computations that make it possible
to perceive, reason and act”,(Winston, 1992)

Think
Rationally

8
 “Computational Intelligence is the study of the
design of intelligent agents” (Poole et al, 1998)
 “AI….is concerned with intelligent behavior in
artifact”, (Nilsson, 1998)

Act Rationally

9
 Acting Humanly: The Turing
Test Approach
http://en.wikipedia.org/wiki/Turing_test

+ physical
interaction =>
Total Turing
Test

- Recognize objects
and gestures
- Move objects

Alan Turing
1912-1954
• To be intelligent, a program should simply act like a
human

10
 To pass the Turing test, the computer/robot needs:
 Natural language processing to communicate successfully.
 Knowledge representation to store what it knows or hears.
 Automated reasoning to answer questions and draw
conclusions using stored information.
 Machine learning to adapt to new circumstances and to detect
and extrapolate patterns.
 Computer vision to perceive objects. (Total Turing test)
 Robotics to manipulate objects and move. (Total Turing test)

 These are the main branches of AI.

11
 1960s “Cognitive Revolution": Information-
processing psychology replaced prevailing
orthodoxy of behaviorism
 Requires scientific theories of internal activities of
the brain. How to validate?
 Cognitive Science: Predicting and testing
behavior of human subjects
 Cognitive Neuroscience: Direct identification from
neurological data
 Both approaches are now distinct from AI, and
share with AI the following characteristic:
 The available theories do not explain (or
engender) anything resembling human-level
general intelligence.
12
 Real intelligence requires thinking  think
like a human !
 First, we should know how a human think
 Introspect ones thoughts
 Physiological experiment to understand
how someone thinks
 Brain imaging – MRI…
 Then, we can build programs and models
that think like humans
 Resulted in the field of cognitive science:
a merger between AI and psychology.

13
 The human thinking process is difficult to
understand: how does the mind raises from the
brain ? Think also about unconscious tasks such
as vision and speech understanding.
 Humans are not perfect ! We make a lot of
systemic mistakes:

14
 Instead of thinking like a human : think
rationally.
 Find out how correct thinking must proceed: the
laws of thought.
 Aristotle syllogism: “Socrates is a man; all men
are mortal, therefore Socrates is mortal.”
 This initiated logic: a traditional and important
branch of mathematics and computer science.
 Problem: it is not always possible to model
thought as a set of rules; sometimes there
uncertainty.
 Even when a modeling is available, the
complexity of the problem may be too large to
allow for a solution.
15
 Rational agent: acts as to achieve the best outcome
 Logical thinking is only one aspect of appropriate
behavior: reactions like getting your hand out of a
hot place is not the result of a careful deliberation,
yet it is clearly rational.
 Sometimes there is no correct way to do, yet
something must be done.
 Instead of insisting on how the program should think,
we insist on how the program should act: we care
only about the final result.
 Advantages:
 more general than “thinking rationally” and more
 Mathematically principled; proven to achieve
rationality unlike human behavior or thought
16
This is how birds fly Humans tried to mimic This is how we finally
birds for centuries achieved “artificial flight”

17
 Rational behavior: doing the right thing
 The right thing: the optimal (best) thing that is
expected to maximize the chances of achieving
a set of goals, in a given situation
 Doesn't necessarily involve thinking, but a
rational agent should be able to demonstrate it
artificially, in moving towards its goal
 Aristotle (Nicomachean Ethics):
 Every art and every inquiry, and similarly
every action and pursuit, is thought to aim at
some good.

18
 An agent is an entity that perceives and acts
 This course is about designing rational/intelligent
agents
 For any given class of environments and tasks, we
seek the agent (or class of agents) with the
optimal (best) performance
 Computational limitations make perfect rationality
unachievable
 So we attempt to design the best (most
intelligent) program, under the given resources.

19
 Philosophy: Logic, methods of reasoning, mind as
physical system, foundations of learning, language,
rationality
 Mathematics: Formal representation and proof,
Algorithms, Computation, (un)decidability,
(in)tractability, probability
 Psychology: Adaptation, phenomena of perception and
motor control, experimental techniques (with animals,
etc.)
 Economics: Formal theory of rational decisions
 Linguistics: Knowledge representation, grammar
 Neuroscience: Plastic physical substrate for mental
activity
 Control theory: Homeostatic systems, Stability, Simple
optimal agent designs.

20
 Gestation of AI (1934 - 1955)
 In 1943, proposed a binary-based model of neurons
 Any computable function can be modeled by a set of neurons
 A serious attempt to model brain
 1950, Turing’s “Computing Machinery and Intelligence ”:
turing test, reinforcement learning and machine learning
 The Inception of AI (1956)
 Dartmouth meeting to study AI
 an AI program ”Logic Theorist” to prove many theorems
 Early Enthusiasm and great Expectation (1952-1969)
 General Problem Solver imitates the human way of thinking
 LISP (AI programming language) was defined
 1965, Robinson discovered the resolution method – logical
reasoning
 AI Winter (1966-1973)
 Computational intractability of many AI problems
 Neural Network starts to disappear
21
 Knowledge-based systems (1969-1979)
 Use domain knowledge to allow for stronger reasoning
 Becomes an Industry (1980-now)
 Digital Equipment Corporation selling R1 “expert
sytem”
 From few million to billions in 8 years
 The return of neural network (1986-now)
 With the back-propagation algorithm
 AI adopts scientific method (1987-now)
 More common to base theorems on pervious ones or
rigorous evidence rather than intuition
 Speech recognition and HMM
 Emergence of intelligent agent (1995-now)
 search engines, recommender systems,….
 Availability of very large data sets (2001 – now)
 Worry more about the data
22
 Robotics Vehicle
 DARPA Challenge
 Speech Recognition
 United Airlines
 Autonomous Planning and Scheduling
 Remote Agent: Plan and control spacecraft
 MAPGEN: daily planning of operations on NASA’s exploration
Rover
 Game Playing
 IBM Deep Blue
 Spam Fighting
 Logistic Planning
 DART – Dynamic Analysis and Replacing Tool
 Gulf War 1991
 To plan the logistic for transportation of 50k vehicles, cargo and
people
 Generated in hour a plan that could take weeks
 Robotics
 Machine Translation
 Statistical models 23
 Speech technologies
 Automatic speech recognition (ASR)
 Text-to-speech synthesis (TTS)
 Dialog systems
 Language Processing Technologies
 Machine Translation
 Information Extraction
 Informtation Retrieval
 Text classification, Spam filtering.

24
25
 Computer Vision:
 Object and Character Recognition
 Image Classification
 Scenario Reconstruction etc.
 Game-Playing
 Strategy/FPS games, Deep Blue etc.
 Logic-based programs
 Proving theorems
 Reasoning etc.

26
27