Download - Artificial Intelligence: INTRODUCTION
ARTIFICIAL INTELLIGENCE:
INTRODUCTION
Short presentation
Dr. Abdullah Alsheddyالشدي. عبدالعزيز عبدالله د
Email : [email protected]: 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%
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
2
Course overview
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)
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
3
Chapter1 : Outline
What is AI A brief history The state of the art
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
4
What is AI?What is AI?
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”
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
5
Intelligent behavior
Humans
Computer
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction6
Why AI? Cognitive Science: As a way to understand how
natural minds and mental phenomena work e.g., visual perception, memory, learning, language, etc.
Philosophy: As a way to explore some basic and interesting (and important) philosophical questions 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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
7
Weak vs. Strong AI
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
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
8
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
9
AI CharacterizationsAI Characterizations
AI CharacterizationsAI Characterizations
Discipline that systematizes and automates intellectual tasks to create machines that :
Act like humansSystem passing the Turing Test (1950)Learning from Knowledge (adapt)Representing Knowledge (memorize)Solve Pb (argue)Understanding (communicate)Theoretical
Act rationallyRational agent (199X)
acts according to his beliefsto reach goals
(not only logical)Pragmatic
Think like humans
Cognitive modeling (GPS (Newel & Simon,61))
Complex
Think rationally logical thinking
Pascal [1623-1662] (calculating machine)
Leibniz [1646-1716] (reasoning machine)
Babbage [1792-1871] (Analytical Engine)
limited / /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
10
Systems that act like humans
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
Test requires the collaboration of major components of AI: knowledge, reasoning, language understanding, learning, …
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
11
Interrogator interacts with a computer and a person. Computer passes the Turing test if interrogator cannot determine which is which.
Systems that act like humans
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
Turing test
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
12
•Prove a theorem•Play chess•Plan a surgical operation•Diagnose a disease•Navigate in a building
Systems that think like humans
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
13
Systems that think rationally 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?
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
14
Systems that act rationally
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
15
Systems that act rationally
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
16
Think/Act RationallyThink/Act Rationally
Always make the best decision given what is available (knowledge, time, resources)
Perfect knowledge, unlimited resources logical reasoning
Imperfect knowledge, limited resources (limited) rationality
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
17
•Connection to economics, operational research, and control theory•But ignores role of consciousness, emotions, fear of dying on intelligence
Rational agents
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:
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
18
f :P* A
Foundations of AI
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
19
A brief history
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
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
20
A brief history (2)
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)
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
21
A brief history (3)
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.
Unrealistic predictions. Some systems lacked scalability.
Combinatorial explosion in search. Fundamental limitations on techniques and representations.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
22
A brief history (4)
AI revival through knowledge-based systems (1969-1970) General-purpose vs. domain specific
E.g. the DENDRAL chemistry project (Buchanan et al. 1969) First successful knowledge intensive system.
Expert systems MYCIN to diagnose blood infections (Feigenbaum et al.)
Introduction of uncertainty in reasoning. Increase in knowledge representation research.
Logic, frames, semantic nets, …
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
23
A brief history (5)
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 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 winter” in which many companies suffered as they failed to deliver on extravagant promisesextravagant promises.
Connectionist revival (1986 - present) Parallel distributed processing (RumelHart and McClelland,
1986); back-propagation learning (computer science and psychology).
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
24
A brief history (6)
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”.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
25
State of the art : AI today 1/2
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.
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
26
Stanley RobotStanford Racing Teamwww.stanfordracing.org
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
27
Major research areas (Applications)
Natural Language Understanding Image, Speech and pattern
recognition Uncertainty Modeling Problem solving Knowledge representation …..
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
28
AI Success Story : Medical expert systems
Antibiotics & InfectiousDiseases
CancerChest painDentistry Dermatology Drugs &
Toxicology Emergency Epilepsy Family PracticeGenetics Geriatrics
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
29
Programs listed by Special Field
Gynecology Imaging Analysis Internal Medicine Intensive Care Laboratory Systems Orthopedics Pediatrics Pulmonology & Ventilation Surgery & Post-Operative
Care Trauma Management
Pattern Recognition Applications
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
30
Handwriting and document recognition
Signature, biometrics (finger, face, iris, etc.)
Trafic monitoring, Remote Sensing
guided missile, target homing
Future of AI
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
31
Making AI Easy to use Easy-to-use Expert system building tools Web auto translation system Recognition-based Interface Packages
Integrated Paradigm Symbolic Processing + Neural Processing
AI in everywhere, AI in nowhere AI embedded in all products Ubiquitous Computing, Pervasive Computing
QuizQuiz
Does a plane fly? Does a boat swim? Does a computer think?
/ /١٤٤٤ ٠٩ ٣٠Artificial Intelligence : Introduction
32