Introduction to AI

Download Report

Transcript Introduction to AI

CS 531: AI
CS 331: Introduction to AI
Dr Mian Muhammad Awais
Room 416
[email protected]
Robotics and Intelligent Computing (RICE), Group
CS 531: Dr M M Awais (LUMS)
Course Description
Course home page: TBA
Contacts:lecture notes, tutorials, assignment, grading, office hours, etc.
Textbooks:
1) Luger: Artificial Intelligence: Structures and Strategies for Complex
Problem-solving Fourth Edition (Available as Reading package)
2) S. Russell and P. Norvig Artificial Intelligence: A Modern Approach
Prentice Hall, 2003, First or Second Edition (HANDOUTS)
Grading:
Quizzes (15%)
Practice (15%),
Midterm test (30%)
Final exam (40%)
Practice Options:
•At least 2 Lab Assignments where attendance will be compulsory and
will be taken.
•Critical reviews of interesting papers
•Take Home/In class Assignments (LISP/PROLOG)
CS 531: Dr M M Awais (LUMS)
TA Support/Office Hours
• TA 1: Umar Faiz ([email protected])
Office hours (TBA, see the website)
• TA 2: TBA
• Instructor Office Hours (room 416):
3 to 4 PM Every day except Friday
[email protected]
CS 531: Dr M M Awais (LUMS)
Course Outline (Core Areas)
Very Basic
• Introduction and Problem Solving
(Today’s Lecture)
• Part I:
Knowledge Representation
• Part II:
Informed Search Methods
• Part III:
Planning / Reasoning/Expert Systems
• Part IV:
Learning
CS 531: Dr M M Awais (LUMS)
Course Outline (Specialized Areas)
• To be decide as the course progresses
• Some options are:
– NLP
– Speech Processing
(On going project at LUMS, 1.0 million, 3 years)
– Agent Technology
(Submitted project, 5.9 million, 3 years)
– Imitative Learning
(On going project at LUMS, 4.3 million, 3 years)
– Case Based Reasoning
– etc
CS 531: Dr M M Awais (LUMS)
Course Format
• Each Class 100 minutes not 75 minutes
• Core Areas:
–
–
–
–
–
Basic stuff,
same as CS 331,
will go through it quickly,
tested with take home assignments,
Midterm and finals will have at least 60% from the core
areas.
• Special Areas:
– High level brief discussion,
– tested with assignments, quizzes,
– maximum of 40% covered in exams
CS 531: Dr M M Awais (LUMS)
Book Chapters
• Book Chapters and articles will be
announced as we go along
• Slides will be available at the website and in
the common’s folder
• Details to be announced later
CS 531: Dr M M Awais (LUMS)
Informal Feedback Mechanism
LETS IMPROVE AS WE MARCH
• Roughly Every Two Weeks an anonymous
questionnaire will be circulated to evaluate
the course
• Your comments will be welcomed to
improve the course as we go along
(DONOT WAIT TILL THE END)
• Course progress discussion
CS 531: Dr M M Awais (LUMS)
Questions
CS 531: Dr M M Awais (LUMS)
TWO PURPOSES of AI.
One is to use the power of computers to augment
human thinking,
just as we use motors to augment human or horse power. Robotics
and expert systems are major branches of that.
The other is to use a computer's artificial
intelligence to understand how humans think.
In a humanoid way. If you test your programs not merely by what
they can accomplish, but how they accomplish it, they you're really
doing cognitive science; you're using AI to understand the human
mind.
Herbert Simon
CS 531: Dr M M Awais (LUMS)
AI Dimensions
1) Modeling:
Thought process/reasoning vs. behavior/action
2) Evaluation:
Success according to human standards vs. success
according to an ideal concept of intelligence
rationality.
CS 531: Dr M M Awais (LUMS)
What is AI?
Views of AI fall into four categories:
Thinking humanly
Thinking rationally
Acting humanly
Acting rationally
CS 531: Dr M M Awais (LUMS)
Thinking humanly
“Can machines think like humans”
• Requires scientific theories of internal activities of
the brain, psychological experiments are required
• Studied in Cognitive Modeling
CS 531: Dr M M Awais (LUMS)
Thinking humanly: cognitive modeling
•1960s "cognitive revolution": information-processing
psychology
•
•Validation Requires
•Predicting and testing behavior of human subjects
(top-down)
•Direct identification from neurological data
(bottom-up)
•Cognitive Science and Cognitive Neuroscience
•Distinct from AI
•
CS 531: Dr M M Awais (LUMS)
Thinking humanly: Some References
–
–
–
–
Daniel C. Dennet. Consciousness explained.
M. Posner (edt.) Foundations of cognitive science
Francisco J. Varela et al. The Embodied Mind
J.-P. Dupuy. The mechanization of the mind
CS 531: Dr M M Awais (LUMS)
Thinking rationally
“Laws of Thought”
“Can machines think rationally”
Several Greek schools developed various forms of logic:
notation and rules of derivation for thoughts; may or may
not have proceeded to the idea of mechanization
CS 531: Dr M M Awais (LUMS)
Thinking rationally
Aristotle: what are correct arguments/thought processes?
Mathematics and Philosophy to Modern AI
Problems:
1. Not all intelligent behavior is mediated by logical deliberation
2. What is the purpose of thinking? What thoughts should I have?
A reference;

Ivan Bratko, Prolog programming for artificial intelligence.
CS 531: Dr M M Awais (LUMS)
Acting humanly
“Can machines behave like Humans?”
“Why and How” is not important
Do what ever you can
CS 531: Dr M M Awais (LUMS)
Acting humanly: Turing Test
• Turing (1950) "Computing machinery and intelligence"
• Operational test for intelligent behavior: the Imitation Game
• Predicted that by 2000, a machine might have a 30% chance of fooling
a lay person for 5 minutes
• Anticipated all major arguments against AI in following 50 years
• Suggested major components of AI: knowledge, reasoning, language
understanding, learning
CS 531: Dr M M Awais (LUMS)
CS 531: Dr M M Awais (LUMS)
Objections :- Turning Test
Most AI Programs Are Not Flexible In Nature
May Not Be Able to Answer Emotional Questions
CS 531: Dr M M Awais (LUMS)
Chinese Room
• The Turing Test was the first attempt at resolving the question of machine
intelligence.
• It was a behavioral test, judging intelligence based not on inner processes, or
faithfulness to neuronal structure, but purely on a computer's ability to
verbally communicate.
• This approach elicited numerous objections:
– Why should behaviour be the final test on intelligence
– How can behavior suffice if the internal mechanisms controlling it are
nothing like a human being's?
– How can a conversation capture all of human intelligence?
• These questions essentially reduced themselves to the question of whether one could
pass the Turing Test, that is, produce passable conversational speech, while still
possessing no 'real' intelligence. This argument has been stated in numerous ways,
but perhaps none more eloquent than
John Searle's Chinese Room metaphor.
http://psych.utoronto.ca/%7Ereingold/courses/ai/
CS 531: Dr M M Awais (LUMS)
Searle Counter Example
• Imagine a room, with a man trapped inside. The man speaks no
Chinese. Someone slips a piece of paper under the door with
Chinese writing on it.
• Having puzzled over it for a moment, he notices that there is a
book in the room titled "What to do if someone slides some
Chinese writing under the door."
• The book, he finds, is actually an enormous set of instructions for
producing new Chinese symbols based on what comes in. The rules
instruct him on how to produce new Chinese symbols, based on the
ones received. They are all if-then type statements describing a
pattern in the text and the appropriate action or response.
• He follows these rules, using the piece of paper handed to him, and
produces a new sheet, which he slides back under the door.
• The next day, another sheet comes in, he passes the completed
sheet back out.
• Outside, the world is amazed that this room can actually
understand Chinese, that the room is intelligent. Inside though, we
know that the man understands
no
Chinese
CS 531: Dr M M
Awais
(LUMS) whatsoever!
Conclusion
What Searle describes is a system that produces
intelligent, meaningful output, in the absence of
true understanding. If you accept this counterexample, then the Turing Test is doomed. The
Chinese Room would pass the Turing test, even
though it lacks understanding and intelligence.
Searle's argument has, naturally, produced its
own share of furious debate, and several strong
counter-arguments have been levelled at it.
CS 531: Dr M M Awais (LUMS)
References
1. http://psych.utoronto.ca/%7Ereingold/cour
ses/ai/cache/chineser.htm
2. http://psych.utoronto.ca/%7Ereingold/cour
ses/ai/cache/searle.html
3. http://consc.net/online2.html (best
resource)
CS 531: Dr M M Awais (LUMS)
Acting rationally
“Can machines behave rationally”
• Rational behavior: doing the right thing
• The right thing: that which is expected to
maximize goal achievement, given the
available information
• Doesn't necessarily involve thinking – e.g.,
blinking reflex – but thinking should be in
the service of rational action
CS 531: Dr M M Awais (LUMS)
What is AI?
Views of AI fall into four categories:
Thinking humanly
Thinking rationally
Acting humanly
Acting rationally
Our Focus is "ACTING RATIONALLY"
CS 531: Dr M M Awais (LUMS)
Rational Agents
• An agent is an entity that perceives and acts
• Every thing to be discussed should be taken in the
context of :
RATIONAL AGENTS
• Abstractly, an agent is a function from percept
histories to actions:
[f: P*  A]
• For a given class of environments/tasks, Rational
Agents sought best performance
CS 531: Dr M M Awais (LUMS)
Limitations:Rational Agents
Computational limitations make
perfect rationality unachievable
References
Michael Wooldridge.
Reasoning about rational
agents.
Design best program for given
machine resources
CS 531: Dr M M Awais (LUMS)
Definition: AI Systems
Artificial Systems that behave rationally
Or
limited rationality
CS 531: Dr M M Awais (LUMS)
Other Aspects
Read it yourself
CS 531: Dr M M Awais (LUMS)
Another Definition: AI?
Computer based solution of complex
problems through the application of
processes that are analogous to the
Human Intelligence
More inclined
towards acting
and thinking
humanly
CONTROVERSIAL ISSUE
(How to define Intelligence?)
CS 531: Dr M M Awais (LUMS)
Intelligence
Reasoning
+
- Establishes Relationships
- Perception and Comprehension
- Generalization Ability
Learning
- Memory/Differentiation
Chair vs Table
Spoon vs Fork
Intelligent Beings
Intelligent Systems
CS 531: Dr M M Awais (LUMS)
Intelligence
Manifestation of intelligence is
through Behavior
CS 531: Dr M M Awais (LUMS)
AI Though Groups
Strong Believers
Weak Believers
CS 531: Dr M M Awais (LUMS)
Weak AI?
Computation
Consciousness
Brain has ingredients that are

Non - computational

Simulating consciousness is not possible
Computational + Non Computational
BRAIN
CS 531: Dr M M Awais (LUMS)
Strong AI ?
Consciousness - “is some complicated computation”
“Computers can achieve or even exceed all Human
Capacities once high computational speeds are
achieved”
Brains Are Computers of MEAT?
CS 531: Dr M M Awais (LUMS)
Strong and Weak AI
1. http://www.ecs.soton.ac.uk/~harnad/Paper
s/Py104/searle.comp.html
CS 531: Dr M M Awais (LUMS)
Scope of AI Based Techniques
Main focus
Problems that do not have
algorithmic solutions, or are very
complex
Vague, uncertain and poor-defined
systems
Systems with decision - making
problems
(Examples?)
CS 531: Dr M M Awais (LUMS)
Example Tasks
Game Playing



Rules are well defined
algorithmic solutions are very complex
Formalization is easy
Automated Reasoning


Theorem proving
Formal logic/ knowledge representation.
Diagnostic
Knowledge
Expert Systems
Mimic experts such as doctors
Experts
Experts
CS 531: Dr M M Awais (LUMS)
Coding
Natural Language Processing



Computer learn human languages
Machine Translation
Speech Synthesis
Planning And Robotics


Artificial Pets.
Efforts to make “machines”
- Responsive
- Flexible
e.g., Path Planning
CS 531: Dr M M Awais (LUMS)
Human Machine
Summary: AI?
• Innovative Extension of Philosophy:
– Understand and BUILD intelligent entities
• Formal Origin after WWII
• Highly interdisciplinary
• Variety of subfields
– This course will discuss some of them
CS 531: Dr M M Awais (LUMS)
AI prehistory
•
Philosophy
•
Mathematics
•
•
•
Economics
Neuroscience
Psychology
•
•
Computer
engineering
Control theory
•
Linguistics
Logic, methods of reasoning, mind as physical
system foundations of learning, language,
rationality
Formal representation and proof algorithms,
computation, (un)decidability, (in)tractability,
probability
Utility, decision theory
Physical substrate for mental activity
Phenomena of perception and motor control,
experimental techniques
Building fast computers
Design systems that maximize an objective
function over time
Knowledge representation, grammar
CS 531: Dr M M Awais (LUMS)
History of AI
•
•
•
•
•
1943
1950
1956
1952—69
1950s
•
•
1965
1966—73
•
•
•
•
•
1969—79
1980-1986-1987-1995--
McCulloch & Pitts: Boolean circuit model of brain
Turing's "Computing Machinery and Intelligence"
Dartmouth meeting: "Artificial Intelligence" adopted
Look, Ma, no hands!
Early AI programs, including Samuel's checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine
Robinson's complete algorithm for logical reasoning
AI discovers computational complexity
Neural network research almost disappears
Early development of knowledge-based systems
AI becomes an industry
Neural networks return to popularity
AI becomes a science
The emergence of intelligent agents
CS 531: Dr M M Awais (LUMS)
State of the art AI
• Deep Blue defeated the reigning world chess champion
Garry Kasparov in 1997
• Proved a mathematical conjecture (Robbins conjecture)
unsolved for decades
• No hands across America (driving autonomously 98% of
the time from Pittsburgh to San Diego)
• During the 1991 Gulf War, US forces deployed an AI
logistics planning and scheduling program that involved up
to 50,000 vehicles, cargo, and people
• NASA's on-board autonomous planning program
controlled the scheduling of operations for a spacecraft
• Proverb solves crossword puzzles better than most
humans
CS 531: Dr M M Awais (LUMS)
First Reading Assignment
(Write a Two Page Summary on What you think AI is)
Submission: Email the article to Instructor /TA by Friday
5:00 pm (or in folder submission_1 in Cs 531AI)
1. Luger’s
Chapter One: Introduction
Other References:
Alexander Igor’s
Impossible minds
(Help Material Available in the Library)
CS 531: Dr M M Awais (LUMS)
Topics Covered Today
• Luger (Some of the discussion is from Stuart and Norvig)
– Part I
– Chapter 1
– Articles 1.1 to 1.4
• Practice:
– Attempt Exercise Questions
– Especially: Qs 1 to 7, 10 to 12
CS 531: Dr M M Awais (LUMS)