Transcript No Slide Title

Artificial Intelligence
Plymouth State College
1
2001: A Space Odyssey
Plymouth State College
12.2
What is Intelligence?
 No good definition
 We think of it as being “human”
 More than the ability to do one task well
 More than manipulating symbols
Plymouth State College
Computers
 Calculate quickly and accurately
 Relieve us of tedious tasks
 Help us to do some tasks better
 Can entertain us (Games)
 Can provide much information (Internet)
Plymouth State College
Artificial Intelligence
 What is AI?
 Group of related technologies used for
development machines to emulate human-like
qualities
Plymouth State College
12.5
Artificial Intelligence
 Types of AI







Virtual reality
Robotics
Natural language processing
Fuzzy logic
Expert systems
Neural networks
Genetic algorithms
Plymouth State College
12.6
Artificial Intelligence
 Some early experiments failed
 A.I. scientists ridiculed
Plymouth State College
Game Playing
 Early days of AI - Researchers thought that teaching
computers to play games such as chess would enable
them to understand something about human
intelligence.
 Found it easy to have computers play games.
 Found it difficult to go beyond game playing and into the realm
of human intelligence.
Plymouth State College
12.8
Easy Computer Problems
Plymouth State College
Difficult Computer Problems
Plymouth State College
“Human” qualities
 Emotion
 Motivation
 Deception
Plymouth State College
Computer “Intelligence”
Plymouth State College
12.12
Computer Control
Plymouth State College
12.13
What is Intelligence—Artificial or
Not?
 The search for intelligence:
 Plato (400 BC) - This Greek philosopher believed that ethereal
spirits were rained down from heaven and entered the body.
 Aristotle (Plato’s student) - The heart must contain the soul and
the brain’s function was to cool the blood.
 Galen - Treated fallen gladiators with spinal cord injuries. Noted
that feeling lost in certain limbs sometimes came back.
 Galvani - Used Benjamin Franklin’s findings about static
electricity to show that static electricity stimulated the nerves
causing a frog to jump.
 Subsequently - Human nervous system found to be a complex
network of billions of neurons.
Plymouth State College
12.14
What is Intelligence—Artificial or
Not?
 Maillardet’s Automaton (1805):
 Object having human form.
 Disguised as a young boy.
 Machine containing levers, ratchets, cams
and other mechanical devices.
 Could draw several complex images.
 Because it had human form and could draw
complex images, a certain feeling of
intelligence was ascribed to the machine.
Plymouth State College
12.15
Artificial Life
 What is artificial life?
 A field of study that deals with computer
instructions that try to simulate human
responses
 What English mathematician and computer
pioneer created a test in 1950 to determine
computer intelligence?
 Alan Turing
Plymouth State College
12.16
What is Intelligence—Artificial or
Not?
 Alan Turing (1912 - 1954)
 Proposed a test - Turing’s Imitation Game
 Tests the intelligence of the computer.
 Attempts to see of a person (Interrogator) can tell the difference
between a human and a computer in answers to questions.
 If the interrogator can’t tell the difference, the computer is
considered to have intelligence.
?
Plymouth State College
12.17
What is Intelligence—Artificial or
Not?
 Claude Shannon’s comparison of the human brain and
the computer:
 Difference in size: The brain has a million more parts.
 Difference in structural organization: The seemingly random local
structure of nerve networks differ vastly from the precise wiring of a
computer.
 Differences in reliability: The brain can operate reliably for decades.
 Differences in logical organization: The brain is largely selforganizing. Digital computers do only a few narrowly defined tasks
well.
 Differences in input-output equipment: Brain is designed with input
organs and output muscles and glands. Computers operate in an
abstract environment of numbers and operations on numbers.
Plymouth State College
12.18
Fundamental Concepts in Artificial
Intelligence
 Rule-based or Expert systems - Consists of rules of
the form IF (condition) THEN (action).
 IF (it is raining AND you must go outside)
 THEN (put on your raincoat)
Plymouth State College
12.19
Expert Systems Components
 Knowledge Base
 “Inference Engine”
 User Interface
Plymouth State College
Expert Systems
 Knowledge of experts
 Understand question (Input)
 Lookup facts and rules (Storage)
 Make decision (Processing)
 Display decision (Output)
Plymouth State College
Expert Systems
 Expert systems are commercially the most successful
domain in Artificial Intelligence.
 IF (some condition) THEN (some action)
 These programs mimic the experts in whatever field.
Auto mechanic
Cardiologist
Organic compounds
Mineral prospecting
Infectious diseases
Diagnostic internal medicine
VAX computer configuration
Engineering structural analysis
Audiologist
Telephone networking
Delivery routing
Professional auditor
Manufacturing
Pulmonary function
Weather forecasting
Battlefield tactician
Space-station life support
Civil law
Plymouth State College
12.22
Expert Systems
 Harold Cohen created an expert system called
AAORN to create art.
Early drawings
by AARON
Plymouth State College
12.23
Expert Systems
 Intelligent Agents:
 Computerized agents that might...
 respond to verbal commands as if it were human.
 be a personal assistant that would access electronic
communications.
 take phone calls.
 make appointments.
 locate individuals by phone.
 find research material.
Plymouth State College
12.24
Fundamental Concepts in Artificial
Intelligence
 For any of these models of the human knowledge
system to work, it must be able to make use of this
knowledge in three different ways:
 Knowledge acquisition - Must be some way of putting
information or knowledge into the system.
 Knowledge retrieval - Must be able to find knowledge when
it is wanted or needed.
 Reasoning with knowledge - Must be able to use that
knowledge through “thinking” or reasoning.
Plymouth State College
12.25
Fundamental Concepts in Artificial
Intelligence
 Knowledge retrieval (by searching):
 Brute-force search - Searching all possible moves, and then
selecting the best.
 Looking for a museum in a small town example:
 Drive around, down every street, until you find one!
 Heuristic search - Uses rules of thumb, intuition. (The
solution is not always guaranteed.)
 Looking for a museum in a small town example:
 Look for the museum down the town’s main street (museums are
usually on the “main street” in small towns!)
Plymouth State College
12.26
Fundamental Concepts in Artificial
Intelligence
 Machine learning: Writing intelligent computer
programs that are capable of learning.
 Example: Teaching a computer to play a game. The more the
computer plays, the more strategies it will learn.
 Common sense:
 The computer must be able to make inferences from the
knowledge base.
 Answers to problems might not be listed.
 The computer will need to come up with its own answers!
 This has been a very difficult area in Artificial Intelligence.
Plymouth State College
12.27
Pattern Recognition
 Humans have the ability to understand or recognize the
relationship among various parts of patterns in: visual
object, sound patterns, smells, and taste.
 Pattern recognition using computers has been
applied in many areas including:






Robot vision
Speech recognition
Fingerprint identification
Handwriting identification
Optical character recognition (OCR)
Weather data analysis and satellite data analysis
Plymouth State College
12.28
Pattern Recognition
 Speech-pattern recognition:
 Problems - Accents, continuous speech,
words that sound the same but are spelled
differently.
 He walked to the store.
 He walked to this door.
 Some commercial products - Some
commercial products do recognize
continuous speech. (not yet perfect)
Plymouth State College
12.29
Game Playing
 Major problem in game playing: How to make the
moves?
 Involves:
 Processing or searching many moves (see game tree)
 By adding heuristics (rules of thumb / intuition), decisions can be
made by the computer as to what is the best move.
Plymouth State College
12.30
Game Playing
 Chess
 MacHack (1974) by Richard Greenblatt of MIT - First program
to compete in a chess tournament.
 Deep Blue (1996) by IBM - Garry Kasparov, world-champion
chess player, won over Deep Blue 4 points to 2.
 Deep Blue (1997) by IBM - Garry Kasparov conceded victory to
Deep Blue, 3.5 points to 2.5.
 The fastest chess-playing program processes 200,000 positions
per second.
 (Thousands of moves more than a human is capable of.)
 Still, the best chess players beat most computer programs.
Plymouth State College
12.31
Natural Language Communication
 The semantics (meaning of the words) is the goal in
communication with the computer.
 Eliza (1965) by Joseph Weizenbaum of MIT
 Simulation of a therapist mirroring a patient’s conversation in a
positive manner.
 The program fooled people into believing it was a therapist.
Plymouth State College
12.32
Natural Language Communication














All men are alike.
IN WHAT WAY
They’re always bugging us about something or other.
CAN YOU THINK OF A SPECIFIC EXAMPLE
Well, my boyfriend made me come here.
YOUR BOYFRIEND MADE YOU COME HERE
He says I’m depressed much of the time.
I AM SORRY TO HEAR YOU ARE DEPRESSED
It’s true, I am unhappy.
DO YOU THINK COMING HERE WILL HELP YOU NOT TO BE UNHAPPY
I need some help, that much seems certain.
WHAT WOULD IT MEAN TO YOU IF YOU GOT SOME HELP
Perhaps I could learn to get along with my mother.
TELL ME MORE ABOUT YOUR FAMILY
 Eliza conversation
Plymouth State College
12.33
Natural Language Communication
 Early failures in natural language translation
 Translation of English to Russian:
 Typed in English (sentence to be translated...):
 The spirit is willing, but the flesh is weak.
 Translated by the program into Russian:
 The vodka is strong, but the meat is rotten.
 Translation programs have come a long way since then!
Plymouth State College
12.34
Neural Networks
 Neuron: Basic building-block of the brain.
 There are several specialized types, but all have the same basic
structure:
 The basic structure of an animal neuron.
Plymouth State College
12.35
Neural Networks
 Artificial models of the brain are of two distinct types:
 Electronic: Has electronic circuits that act like neurons.
 Software: This version runs a program on the computer that
simulates the action of the neurons.
Plymouth State College
12.36
Neural Networks
 Neural Network:
 A collection of neurons which are interconnected.
 The output of one connects to several others with different
strength connections.
 Initially, neural networks have no knowledge. (All information is
learned from experience using the network.)
Neuron 1
Input 1
Output from
Neuron 1
Input 2
Input 3
Neuron 2
Plymouth State College
Output from
Neuron 2
12.37
Fuzzy Logic
 Probability that a statement is true
 Combined with other AI technologies
 Washing Machine
 Variable speed limits
Plymouth State College
Finding Information
 Intelligent agent
 Software that performs work tasks
 Example: monster.com
Plymouth State College
12.39
Next Week
 Your PowerPoint presentation is due
 You will be able to present it in class for extra
credit
Plymouth State College
12.40
Exam in Two Weeks
Chapters 7 & 8 from the Textbook
Lectures since Exam 2
Final Exam Week
 Final exam is scheduled Tue. & Thu. 5:00 – 6:15
 You may take it on either day
Plymouth State College
12.42