ARTIFICIAL INTELLIGENCE:
INTRODUCTION
Short presentation
2
Dr. Abdullah Alsheddy
‫ عبدهللا عبدالعزيز الشدي‬.‫د‬
Email : alsheddy@ccis.imamu.edu.sa
Office: FR64
Textbook:
S. Russell and P. Norvig Artificial Intelligence: A Modern Approach, Prentice
Hall, 3rd Edition, 2009
Grading:




Quizzes/Presentation/Participation (20%)
Project (20%)
Midterm test (20%)
Final Exam: 40%
Artificial Intelligence : Introduction
24/06/1436
Course overview
3







Introduction and Agents (chapters 1,2)
Search (chapters 3,4,5,6)
Logic (chapters 7,8,9)
Planning (chapters 11,12)
Uncertainty (chapters 13,14)
Learning (chapters 18,20)
Robotics (chapter 25,26)
Artificial Intelligence : Introduction
24/06/1436
Chapter1 : Outline
4



What is AI
A brief history
The state of the art
Artificial Intelligence : Introduction
24/06/1436
What is AI?
5

Intelligence:


“the capacity to learn and solve problems” (Websters dictionary)
in particular,




the ability to solve novel problems
the ability to act rationally
the ability to act like humans
Artificial Intelligence


build and understand intelligent entities or agents
2 main approaches: “engineering” versus “cognitive modeling”
Artificial Intelligence : Introduction
24/06/1436
Intelligent
behavior
Computer
Humans
6
Artificial Intelligence : Introduction
24/06/1436
Why AI?
7

Cognitive Science: As a way to understand how natural minds
and mental phenomena work


Philosophy: As a way to explore some basic and interesting
(and important) philosophical questions


e.g., visual perception, memory, learning, language, etc.
e.g., the mind body problem, what is consciousness, etc.
Engineering: To get machines to do a wider variety of useful
things

e.g., understand spoken natural language, recognize individual people
in visual scenes, find the best travel plan for your vacation, etc.
Artificial Intelligence : Introduction
24/06/1436
Weak vs. Strong AI
8




Weak AI: Machines can be made to behave as if they were
intelligent
Strong AI: Machines can have consciousness
Subject of fierce debate among philosophers and AI
researchers.
E.g. Red Herring article and responses

http://groups.yahoo.com/group/webir/message/1002
Artificial Intelligence : Introduction
24/06/1436
AI Characterizations
9
Artificial Intelligence : Introduction
24/06/1436
AI Characterizations
10
Discipline that systematizes and automates
intellectual tasks to create machines that :
Act like humans
System passing the Turing Test (1950)
Learning from Knowledge (adapt)
Representing Knowledge (memorize)
Solve Pb (argue)
Understanding (communicate)
Theoretical
Think like humans
Cognitive modeling
(GPS (Newel & Simon,61))
Complex
Act rationally
Rational agent (199X)
acts according to his beliefs
to reach goals
(not only logical)
Pragmatic
Think rationally
logical thinking
Pascal [1623-1662] (calculating machine)
Leibniz [1646-1716] (reasoning machine)
Babbage [1792-1871] (Analytical Engine)
limited
Artificial Intelligence : Introduction
24/06/1436
Systems that act like humans
11

When does a system behave intelligently?



Turing (1950) Computing Machinery and Intelligence
"Can machines think?"  "Can machines behave intelligently?"
Operational test of intelligence: imitation games
Interrogator interacts with a computer and
a person.
Computer passes the Turing test if
interrogator cannot determine which is
which.

Test requires the collaboration of major components of AI: knowledge,
reasoning, language understanding, learning, …
Artificial Intelligence : Introduction
24/06/1436
Systems that act like humans
12



AI is the art of creating machines that perform
functions that require intelligence when
performed by humans
Methodology: Take an intellectual task at which
people are better and make a computer do it
•Prove a theorem
Turing test
•Play chess
•Plan a surgical operation
•Diagnose a disease
•Navigate in a building
Artificial Intelligence : Introduction
24/06/1436
Systems that think like humans
13

How do humans think?

Requires scientific theories of internal brain activities (cognitive model):

How to validate?






requires :
Predicting and testing human behavior
Identification from neurological data
Brain imaging in action
Cognitive Science vs. Cognitive neuroscience vs. Neuroimaging
They are now distinct from AI
Share that the available theories do not explain
anything resembling human intelligence.

Three fields share a principal direction.
Artificial Intelligence : Introduction
24/06/1436
Systems that think rationally
14

Capturing the laws of thought
 Aristotle:
What are ‘correct’ argument and thought
processes?

Correctness depends on irrefutability of reasoning processes.
 This

study initiated the field of logic.
The logicist tradition in AI hopes to create intelligent systems using logic
programming.
 Problems:


Not all intelligence is expressed by logic behavior
What is the purpose of thinking? What thought should one have?
Artificial Intelligence : Introduction
24/06/1436
Systems that act rationally
15

Rational behavior: “doing the right thing”
 The
“Right thing” is that what is expected to maximize goal
achievement given the available information.

Can include thinking, yet in service of
rational action.
 Action
without thinking: e.g. reflexes.
Artificial Intelligence : Introduction
24/06/1436
Systems that act rationally
16

Two advantages over previous approaches:




More general than law of thoughts approach
More amenable to scientific development.
Yet rationality is only applicable in ideal environments.
Moreover rationality is not a very good model of
reality.
Artificial Intelligence : Introduction
24/06/1436
Think/Act Rationally
17



Always make the best decision given what is
available (knowledge, time, resources)
Perfect knowledge, unlimited resources  logical
reasoning
Imperfect knowledge, limited resources  (limited)
rationality
•Connection to economics, operational research,
and control theory
•But ignores role of consciousness, emotions,
fear of dying on
intelligence
Artificial Intelligence : Introduction 24/06/1436
Rational agents
18


An agent is an entity that perceives and acts
This course is about designing rational agents

An agent is a function from percept histories to actions:
f : P*  A


For any given class of environments and task we seek the agent (or class
of agents) with the best performance.
Problem: computational limitations make perfect rationality
unachievable.

Artificial Intelligence : Introduction
24/06/1436
Foundations of AI
19

Different fields have contributed to AI in the form of
ideas, view points and techniques.







Philosophy: Logic, reasoning, mind as a physical system, foundations of learning,
language and rationality.
Mathematics: Formal representation and proof algorithms, computation,
(un)decidability, (in)tractability, probability.
Psychology: adaptation, phenomena of perception and motor control.
Economics: formal theory of rational decisions, game theory.
Linguistics: knowledge representation, grammar.
Neuroscience: physical substrate for mental activities.
Control theory: homeostatic systems, stability, optimal agent design.
Artificial Intelligence : Introduction
24/06/1436
A brief history
20

What happened after WWII?

1943: Warren Mc Culloch and Walter Pitts: a model of artificial
boolean neurons to perform computations.



First steps toward connectionist computation and learning (Hebbian learning).
Marvin Minsky and Dann Edmonds (1951) constructed the first neural network
computer
1950: Alan Turing’s “Computing Machinery and Intelligence”


First complete vision of AI.
Idea of Genetic Algorithms
Artificial Intelligence : Introduction
24/06/1436
A brief history (2)
21

The birth of (the term) AI (1956)

Darmouth Workshop bringing together top minds on automata theory,
neural nets and the study of intelligence.



Allen Newell and Herbert Simon: The logic theorist (first non-numerical thinking program
used for theorem proving).
For the next 20 years the field was dominated by these participants.
Great expectations (1952-1969)

Newell and Simon introduced the General Problem Solver.



Imitation of human problem-solving
Arthur Samuel (1952-) investigated game playing (checkers ) with great success.
John McCarthy(1958-) :


Inventor of Lisp (second-oldest high-level language)
Logic oriented, Advice Taker (separation between knowledge and reasoning)
Artificial Intelligence : Introduction
24/06/1436
A brief history (3)
22

The birth of AI (1956)

Great expectations continued ..

Marvin Minsky (1958 -)





Introduction of microworlds that appear to require intelligence to solve: e.g. blocks-world.
Anti-logic orientation, society of the mind.
Herbert Gelernter (1959) : constructed the geometry theorem Prover.
Artur Samual (1952-1956) : a series of programs for checkers.
Collapse in AI research (1966 - 1973)

Progress was slower than expected.


Some systems lacked scalability.


Unrealistic predictions.
Combinatorial explosion in search.
Fundamental limitations on techniques and representations.
Artificial Intelligence : Introduction
24/06/1436
A brief history (4)
23

AI revival through knowledge-based systems
(1969-1970)

General-purpose vs. domain specific

E.g. the DENDRAL chemistry project (Buchanan et al. 1969)


Expert systems

MYCIN to diagnose blood infections (Feigenbaum et al.)


First successful knowledge intensive system.
Introduction of uncertainty in reasoning.
Increase in knowledge representation research.

Logic, frames, semantic nets, …
Artificial Intelligence : Introduction
24/06/1436
A brief history (5)
24


AI becomes an industry (1980 - present)

First successful commercial expert system R1 at DEC (McDermott, 1982)

Fifth generation project in Japan (1981) : a 10-year plan to build intelligent computer
running Prolog.

American response …: US formed the microelectronics and Computer Technology
Corporation designed to assure national competitiveness (chip design and human-interface
research)
Puts an end to the AI winter.
AI industry boomed from a few million to billion dollars in 1988. Period called “AI winter” in
which many companies suffered as they failed to deliver on extravagant promises.

Connectionist revival (1986 - present)

Parallel distributed processing (RumelHart and McClelland, 1986);
back-propagation learning (computer science and psychology).
Artificial Intelligence : Introduction
24/06/1436
A brief history (6)
25

AI becomes a science (1987 - present)






In speech recognition: hidden markov models
In neural networks
In uncertain reasoning and expert systems: Bayesian network formalism
Problem solving
…
The emergence of intelligent agents (1995 - present)

The whole agent problem:
“How does an agent act/behave embedded in real environments with continuous sensory
inputs”
“Ideally, an intelligent agent takes the best possible action in a situation : study the
problem of building intelligent agents in this sense”.
Artificial Intelligence : Introduction
24/06/1436
State of the art : AI today
1/2
26





Autonomous planning and scheduling : on-board autonomous planning
program to control the scheduling of operations for a spacecraft (Jonhson
et al., 2000).
Game playing : IBM’s Deep Blue became the first computer program to
defeat the world champion in chess match (Goodman and Keene, 1997),
Autonomous control : the ALVINN computer vision system was trained to
steer a car to keep it following a lane (for 2850 miles ALVINN was in
control of steering in 98%, only 2% for human control mostly at exit ramps).
Diagnosis : medical diagnosis programs based on probabilistic analysis
have been able to perform at level of an expert physician in several areas
in medicine (Heckerman 1991).
Robot driving: DARPA grand challenge 2003-2007.
Artificial Intelligence : Introduction
24/06/1436
Stanley RobotStanford Racing Team
www.stanfordracing.org
27
Artificial Intelligence : Introduction
24/06/1436
Major research areas (Applications)
28
Natural Language Understanding
 Image, Speech and pattern recognition
 Uncertainty Modeling
 Problem solving
 Knowledge representation
 …..

Artificial Intelligence : Introduction
24/06/1436
AI Success Story : Medical expert systems
29
Programs listed by Special Field
Antibiotics & Infectious
Diseases
Cancer
Chest pain
Dentistry
Dermatology
Drugs &
Toxicology
Emergency
Epilepsy
Family Practice
Genetics
Geriatrics











Gynecology
Imaging Analysis
Internal Medicine
Intensive Care
Laboratory Systems
Orthopedics
Pediatrics
Pulmonology & Ventilation
Surgery & Post-Operative
Care
Trauma Management
Artificial Intelligence : Introduction
24/06/1436
Pattern Recognition Applications
30

Handwriting and document recognition

Signature, biometrics (finger, face, iris, etc.)

Trafic monitoring, Remote Sensing

guided missile, target homing
Artificial Intelligence : Introduction
24/06/1436
Future of AI
31

Making AI Easy to use




Integrated Paradigm


Easy-to-use Expert system building tools
Web auto translation system
Recognition-based Interface Packages
Symbolic Processing + Neural Processing
AI in everywhere, AI in nowhere


AI embedded in all products
Ubiquitous Computing, Pervasive Computing
Artificial Intelligence : Introduction
24/06/1436
Quiz
32



Does a plane fly?
Does a boat swim?
Does a computer think?
Artificial Intelligence : Introduction
24/06/1436