Artificial Intelligence - Basic Principles

periodicdollsAI and Robotics

Jul 17, 2012 (4 years and 11 months ago)

873 views

CS-360
Artificial Intelligence
Fall 2011
1
Organizational Details
Class Meeting:
1:00pm-3:45pm; Monday; Room SCIT-215
Instructor: Dr. Igor Aizenberg
Office: Science and Technology Building, 104C
Phone 903-334 6654
e-mail: igor.aizenberg@tamut.edu
Office hours:
Monday noon-1pm, 4:30 – 5:30; Tuesday noon-4pm;
Wednesday, 1:30pm-5:30pm
Class Web Page
:http://www.eagle.tamut.edu/faculty/igor/CS-360.htm
2
Text Book
• Artificial Intelligence: Modern Approach
by Stuart J. Russell and Peter Norvig,
3
rd
edition. Prentice Hall;
• ISBN-10: 0136042597, ISBN-13:
9780136042594
3
Control
Projects - Tests
Project-Test 1:
October 10, 2011
Project-Test 2:
November 14, 2011
Project-Test 3:
December 12, 2011
Homework
4
Grading
Grading Method
Each project-test will be graded and the
final grade will be the average over all the
projects grades
Grading Scale:
90%+ A
80%+ B
70%+ C
60%+ D
less than 60% F
5
Questions of (Artificial)
Intelligence
• How can a limited brain respond to the
incredible variety of world experience?
(cognitive science)
• How can a system learn to respond to new
events? (cognitive science and AI)
• How can a computational system model or
simulate perception? Reasoning? Action?
(AI)
What is Artificial Intelligence?
• Understand and develop computations to
– Reason, learn, and perceive
• Reasoning:
– Expert systems, planning, uncertain reasoning
– E.g. Route finders, Medical diagnosis, Deep Blue
• Learning:
– Identifying regularities in data, generalization
– E.g. Recommender systems, Spam filters
• Perception:
– Vision, robotics, language understanding

E.g. Face trackers, Mars rover, ASR, Google
What is Artificial Intelligence?
“The exciting new effort to
make computers thinks …
machine with minds,in the full
and literal sense”
(Haugeland 1985)
“The art of creating machines
that perform functions that
require intelligence when
performed by people”
(Kurzweil, 1990)
“The study of mental faculties
through the use of computational
models”
(Charniak et al. 1985)
“A field of study that seeks to
explain and emulate intelligent
behavior in terms of
computational processes”
(Schalkol, 1990)
Systems that think like humans
Systems that think rationally
Systems that act like humans
Systems that act rationally
What is Artificial Intelligence?
Search engines
Robotics
Control
Medicine/
Diagnosis
Appliances
CS 460, Lecture 1
Acting Humanly: The Turing Test
• Alan Turing's 1950 article Computing Machinery and
Intelligence discussed conditions for considering a machine to
be intelligent
– “Can machines think?” ←→“Can machines behave intelligently?”

The Turing test (The Imitation Game): a computer passes the test if a
human interrogator, after posing some questions, cannot distinguish
between answers given by a human and a computer (Operational
definition of intelligence)
Acting Humanly: The Turing Test
• Computer needs to posses:
Natural language processing to enable it to
communicate
Knowledge representation to store what it learns
and knows
Automated reasoning to use the stored
information to answer questions and to draw
conclusions
Machine learning to adapt to different
circumstances and to extrapolate patterns
11
Acting Humanly: The Turing Test
• Total Turing Test also includes:
Computer vision to perceive objects
Motor control (robotics) to manipulate objects
and move

Other senses (such as audition, smell, touch,
etc.)
12
Thinking Humanly:
Cognitive Science

1960 “Cognitive Revolution”: information-processing
psychology
• Cognitive science brings together theories and
experimental evidence to model internal activities of
the brain
– What level of abstraction? “Knowledge” or “Circuits”?
– How to validate models?
• Predicting and testing behavior of human subjects (top-down)
• Direct identification from neurological data (bottom-up)
• Building computer/machine simulated models and reproduce results
(simulation)
Thinking Rationally:
Laws of Thought

Aristotle (~ 450 B.C.) attempted to codify “right thinking”
What are correct arguments/thought processes?

E.g., “Socrates is a man, all men are mortal; therefore
Socrates is mortal”

Several Greek schools developed various forms of logic:
notation plus rules of derivation for thoughts.
Thinking Rationally:
Laws of Thought

Problems:
1)
Uncertainty: Not all facts are certain (e.g., the flight might
be delayed).
2) Resource limitations:
- Not enough time to compute/process
- Insufficient memory/disk/etc
-
Etc.
Acting Rationally:
The Rational Agent

Rational behavior: Doing the right thing!

The right thing: That which is expected to maximize the
expected return
• Provides the most general view of AI because it includes:
– Correct inference (“Laws of thought”)
– Uncertainty handling
– Resource limitation considerations

Cognitive skills (natural language processing, automated reasoning,
knowledge representation, machine learning, etc.)

Advantages:
1) More general
2) Its goal of rationality is well defined
Acting Rationally:
The Rational Agent
• Rational decisions
• Rational: maximally achieving pre-defined
goals
• Rational only concerns what decisions are
made (not the thought process behind them)
• Goals are expressed in terms of the utility of
outcomes
• Being rational means maximizing your
expected utility
How to achieve
Artificial Intelligence?

How is AI research done?

AI research has both theoretical
and experimental
sides. The experimental side has both basic and
applied aspects.
• There are two main lines of research:
– One is biological,based on the idea that since humans are intelligent, AI
should study humans and imitate their psychology or physiology.
– The other is phenomenal, based on studying and formalizing common
sense facts about the world and the problems that the world presents to
the achievement of goals.
• The two approaches interact to some extent
Branches of Artificial Intelligence
• Logical AI
• Search
• Natural language processing
• Pattern recognition and Machine Learning
• Knowledge representation
• Inference From some facts, others can be inferred.
• Automated reasoning
• Learning from experience
• Planning To generate a strategy for achieving some goal
• Epistemology Study of the kinds of knowledge that are required for solving
problems in the world.
• Ontology Study of the kinds of things that exist. In AI, the programs and sentences
deal with various kinds of objects, and we study what these kinds are and what
their basic properties are.
• …
CS 460, Lecture 1
Artificial Intelligence Prehistory
Herb Simon, 1957
• “It is not my aim to surprise or shock you, but the
simplest way I can summarize is to say that there are
now in the world machines that think, that learn and
that create. Moreover, their ability to do these things is
going to increase rapidly until in a visible future the
range of problems they can handle will be coextensive
with the range to which human mind has been applied.
• More precisely: within 10 years a computer would be
chess champion, and an important new mathematical
theorem would be proved by a computer.”
21
Herb Simon, 1957
• Herb Simon’s prediction came true, but after
roughly xc 40 years instead of after 10
• Particularly, in 1997 the “Deep Blue”
computer chess program defeated world
champion Garry Kasparov, proving
mathematical theorems using a computer
became regular, etc.
22
CS 460, Lecture 1
Artificial Intelligence History
Artificial Intelligence:
State of the art
• The following have been achieved by AI:
– World-class chess playing
– Playing table tennis, soccer, etc.
– Cross-country driving
– Automated proving of mathematical theorems and solving
routine mathematical problems
– Engage in a meaningful conversation
– Understand spoken language
– Solving various pattern recognition problems
– Observe and understand human emotions
– Express emotions
– …
What Can Artificial Intelligence do?
• Quiz: Which of the following can be done at present?
• Play a decent game of table tennis?
• Drive safely along a curving mountain road?
• Buy a week's worth of groceries on the web?
• Buy a week's worth of groceries at Walmart?
• Discover and prove a new mathematical theorem?
• Converse successfully with another person for an hour?
• Perform a complex surgical operation?
• Unload a dishwasher and put everything away?
• Translate spoken Chinese into spoken English in real time?
• Compose Music?

Write an intentionally funny story?
25
What Can Artificial Intelligence do?
• Quiz: Which of the following can be done at present?

Play a decent game of table tennis?

Yes

Drive safely along a curving mountain road?

Yes

Buy a week's worth of groceries on the web?

Yes
• Buy a week's worth of groceries at Walmart? No
• Discover and prove a new mathematical theorem? Should be
• Converse successfully with another person for an hour? No
• Perform a complex surgical operation? No
• Unload a dishwasher and put everything away? Should be

Translate spoken Chinese into spoken English in real time?

Yes

Compose Music?

Yes
• Write an intentionally funny story? No
26
Unintentionally Funny Stories
1) One day Joe Bear was hungry. He asked his friend Irving
Bird where some honey was. Irving told him there was a
beehive in the oak tree. Joe walked to the oak tree. He ate
the beehive. The End.
2) Henry Squirrel was thirsty. He walked over to the river
bank where his good friend Bill Bird was sitting. Henry
slipped and fell in the river. Gravity drowned. The End.
3) Once upon a time there was a dishonest fox and a vain
crow. One day the crow was sitting in his tree, holding a
piece of cheese in his mouth. He noticed that he was
holding the piece of cheese. He became hungry, and
swallowed the cheese. The fox walked over to the crow.
The End.
• [Shank, Tale-Spin System, 1984]
27
Studying Artificial Intelligence
• Develop principles for rational agents
– Implement components to construct
• Knowledge Representation and Reasoning
– What do we know, how do we model it, how
we manipulate it
• Search, constraint propagation, Logic, Planning
• Machine learning
• Applications to perception and action
– Language, speech, vision, robotics.
Designing Rational Agents
• An agent is an entity that perceives and acts
• A rational agent selects actions that maximize
its utility function
• Characteristics of the percepts, environment,
and action space dictate techniques for
selecting rational actions
29
Designing Rational Agents
30
Agent
Sensors
?
Actuators
E
n
v
i
r
o
n
m
e
n
t
Perception
Action
Situated Agents
• Agents operate in and with the environment
– Use sensors to perceive environment
• Percepts
– Use actuators to act on the environment
• Agent function
– Percept sequence -> Action
• Conceptually, table of percepts/actions defines agent
• Practically, implement as program operating on some
hardware
Situated Agent Example
• Vacuum cleaner:
– Percepts: Location (A,B); Dirty/Clean
– Actions: Move Left, Move Right; Vacuum
• A,Clean -> Move Right
• A,Dirty -> Vacuum
• B,Clean -> Stop
• B,Dirty -> Vacuum
So what we will study?
• General AI techniques for a variety of problem
types
• Learning to recognize when and how a new
problem can be solved with an existing
technique
33