Transcript Document

Artificial Intelligence
Hassan Najadat
Jordan University of Science &
Technology
CS 362
SLIDE 1
Outline
•
•
•
•
Course Overview
What is AI ?
A brief history
The state of the art
CS 362
SLIDE 2
Course Overview
• Intelligent agent
• Problem Solving
–
–
–
–
Solving problems by searching
Informed Search and Exploration
Constraint Satisfaction Problems
Adversarial Search
• Logical system
–
–
–
–
Logical Agent
First Order Logic
Inference in First-Order Logic
Knowledge Representation
• Learning from Observations
CS 362
SLIDE 3
What is AI ?
“Like People”
“Rationally”
Think
Cognitive
Science
Laws of
Thought
Act
Turing Test
Rational Agents
CS 362
SLIDE 4
What is AI ?
Systems that think like humans
Systems that think rationality
``The exciting new effort to make
computers think ... machines 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)
``The study of mental faculties through the
use of computational models'' (Charniak
and McDermott, 1985)
``The study of the computations that make
it possible to perceive, reason, and act''
(Winston, 1992)
Systems that act like humans
Systems that act like rationality
``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
are better'' (Rich and Knight, 1991)
``A field of study that seeks to explain and
emulate intelligent behavior in terms of
computational processes'' (Schalkoff,
1990)
``The branch of computer science that is
concerned with the automation of
intelligent behavior'' (Luger and
Stubblefield, 1993)
CS 362
SLIDE 5
Acting humanly: The Turing Test approach
•
The Turing Test, proposed by Alan Turing (Turing, 1950), was
designed to provide a satisfactory operational definition of
intelligence.
•
The computer would need to possess the following
capabilities:
1.
2.
3.
4.
•
Natural language processing to enable it to communicate successfully in
English (or some other human language);
Knowledge representation to store information provided before or during the
interrogation;
Automated reasoning to use the stored information to answer questions and
to draw new conclusions;
Machine learning to adapt to new circumstances and to detect and
extrapolate patterns.
To pass the total Turing Test, the computer will need
•
•
CS 362
Computer Vision
Robotics
SLIDE 6
Example
Natural Language (NL) Processing
1.
2.
3.
4.
5.
6.
•
•
noun
verb
determiner
adjective
adverb
pronoun
s --> det, noun, verb, det, noun.
a better version
– s --> np, verb.
s --> np, verb, np.
np --> det, adj*, noun.
np --> proper-name.
np --> pronoun.
CS 362
SLIDE 7
Thinking humanly: The cognitive modeling approach
- Program thinks like a human ..!
We need to get inside the actual workings of human minds.
There are two ways:
– through introspection--trying to catch our own thoughts as they
go by—
– or through psychological experiments.
• GPS -``General Problem Solver''
– (GPS) A procedure and program developed by Allen Newell, J.
C. Shaw, and Herbert Simon.
– GPS attains an objective by using recursive search and by
applying rules to generate the alternatives at each branch in the
recursive expansion of possible sequences.
– GPS uses a procedure to measure the "distance" from the goal.
CS 362
SLIDE 8
Thinking rationality: The Logical approach
• Ensure that all actions performed by computer are
justifiable (“rational”)
Facts and Rules
in Formal Logic
Theorem Prover
• Rational = Conclusions are provable from inputs and
prior knowledge
• Problems:
– Representation of informal knowledge is difficulty
– Hard to define “provable” plausible reasoning
– Combinatorial explosion: Not enough time or space to prove
desired conclusions.
CS 362
SLIDE 9
Acting rationally: The rational agent approach
• Rational behavior : doing the right thing ( that which is
expected to maximize goal achievement, given the available
information).
• Agent
• Program
• Agent and Program
• Rational Agent is one that acts to achieve the best outcomes
or, when there is uncertainty, the best expected outcome.
Rational agents do the best they can
given their resources
CS 362
SLIDE 10
Rational Agents
very few resources
no thought
“reflexes”
lots of resources
limited,
approximate
reasoning
Careful, deliberate
reasoning
• Adjust amount of reasoning according to
available resources and importance of
the result
• This is one thing that makes AI hard
CS 362
SLIDE 11
CS 362
SLIDE 12
CS 362
SLIDE 13
Areas of Study in AI
• Reasoning, optimization, resource allocation
– planning, scheduling, real-time problem solving,
intelligent assistants, internet agents
• Natural Language Processing
– information retrieval, summarization, understanding,
generation, translation
• Vision
– image analysis, recognition, scene understanding
• Robotics
– grasping/manipulation, locomotion, motion planning,
mapping
CS 362
SLIDE 14
Where are we now?
• SKICAT: a system for automatically classifying the
terabytes of data from space telescopes and identifying
interesting objects in the sky. 94% classification
accuracy, exceeds human abilities.
• Deep Blue: the first computer program to defeat
champion Garry Kasparov.
• Pegasus: a speech understanding program that is a
travel agent (1-877-LCS-TALK).
• Jupiter: a weather information system (1-888-573-TALK)
• HipNav: a robot hip-replacement surgeon.
CS 362
SLIDE 15
Where are we now?
• Navlab: a Ford escort that steered itself from Washington
DC to San Diego 98% of the way on its own!
• google news: autonomous AI system that assembles
“live” newspaper
• DS1: a NASA spacecraft that did an autonomous flyby
an asteroid.
• Credit card fraud detection and loan approval
• Search engines: www.citeseer.com, automatic
classification and indexing of research papers.
• Proverb: solves NYT puzzles as well as the best
humans.
CS 362
SLIDE 16
Surprises in AI research
• Tasks difficult for humans have turned out to be
“easy”
–
–
–
–
–
–
–
–
CS 362
Chess
Checkers, Othello, Backgammon
Logistics planning
Airline scheduling
Fraud detection
Sorting mail
Proving theorems
Crossword puzzles
SLIDE 17
Surprises in AI research
• Tasks easy for humans have turned out to be
hard.
–
–
–
–
–
–
–
CS 362
Speech recognition
Face recognition
Composing music/art
Autonomous navigation
Motor activities (walking)
Language understanding
Common sense reasoning (example: how many legs
does a fish have?)
SLIDE 18