Upload
others
View
17
Download
0
Embed Size (px)
Citation preview
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley
Chapter 11:
Artificial Intelligence
Computer Science: An Overview
Tenth Edition
by
J. Glenn Brookshear
Presentation files modified by Farn Wang
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-2
Chapter 11: Artificial Intelligence
• 11.1 Intelligence and Machines
• 11.2 Perception
• 11.3 Reasoning
• 11.4 Additional Areas of Research
• 11.5 Artificial Neural Networks
• 11.6 Robotics
• 11.7 Considering the Consequences
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-3
Intelligent Agents
• Agent: A “device” that responds to stimuli
from its environment
– Sensors
– Actuators
• Much of the research in artificial
intelligence can be viewed in the context of
building agents that behave intelligently
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-4
Artificial intelligence
- coining the buzzword
John McCarthy, Dartmouth College
summer, 1956
• suggested a study of artificial intelligence
be carried out
• to explore the conjecture that every aspect
of learning or any other feature of
intelligence can in principle be so precisely
described that a machine can be made to
simulate it.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-5
Levels of Intelligent Behavior
• Reflex: actions are predetermined
responses to the input data
– Is “kick on knocking” intelligent ?
– Is swimming intelligent ?
– Is bike riding intelligent ?
• More intelligent behavior requires
knowledge of the environment and
involves such activities as:
– Goal seeking
– Learning
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-6
Intelligence in reflexion
Look at the
center
wheel.
Tell me
what the
other
wheels
are doing ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-7
Intelligence in reflexion
Which cycles are rotating ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-8
Intelligence in reflexion
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-9
Intelligence in reflexion
What is
the color
of the
empty
dot ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-10
Intelligence in reflexion
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-11
Intelligence in reflexion
Which rectangle is
taller ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-12
Intelligence in reflexion
Which rectangle is
taller ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley
What is intelligence ?
• It is needed in solving difficult problems
with no guaranteed solutions.
• It cannot be prescribed as a fixed set of
rules.
• It relies on common senses.
• It must be adaptive with learning
capabilities.
• It works most of the time, but may fail
occasionally.
11-13
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-14
The eight-puzzle
- a game needs multitudes of intelligence
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-15
Our puzzle-solving machine
• Taking photos of
the puzzle.
• Recognize the
configuration of the
puzzle.
• Compute the next
move.
• Move the tiles.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-16
Approaches to Research in Artificial
Intelligence
• Engineering track
– Performance oriented
• Theoretical track
– Simulation oriented
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-17
Turing Test
• Test setup: Human interrogator
communicates with test subject by
typewriter.
• Test: Can the human interrogator
distinguish whether the test subject is
human or machine?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-18
Techniques for Understanding Images
• Template matching
• Two steps approach:
– Image processing
• edge enhancement
• region finding
• smoothing
– Image analysis
• motion detection
• face recognization
• ……
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-19
Techniques for Understanding
Images for the puzzle
• Template matching
– 3-D pattern matching is difficult.
– restrictive and difficult to scale!
• Two steps approach:
– Image processing
– Image analysis
• to recognize a tile with different focal lengths and
angles.
• to recognize a number with various fonts and hand
writings.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-20
Language Processing
• Syntactic Analysis
• Semantic Analysis
– knowledge representation
– knowledge retrieval
• Contextual Analysis
– interpretation of sentences according to
contexts
– common senses
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-21
Language Processing
Syntactic Analysis
Cinderella had a ball.
subject verb object.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-22
Language Processing
Syntactic Analysis
Stampeding cattle can be dangerous.
subject ? verb
subject ?
object ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-23
Language Processing
Semantic Analysis
Mary gave John a birthday card.
John got a birthday card from Mary.
• knowledge representation
– how to represent the true meaning ?
• information retrieval
– key words ?
• information extraction
– frames, templates ?
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-25
Language Processing
Contextual Analysis
• interpretation of sentences according to
contexts
Cinderella had a ball.
Do you know what time it is ?
• common senses
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-26
Production Systems (Expert systems)
Components
1. Collection of states
– Start (or initial) state
– Goal state (or states)
2. Collection of productions: rules or moves
– Each production may have preconditions
3. Control system: decides which production
to apply next
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-27
Production Systems (Expert systems)
Components
1. Collection of states
2. Collection of productions: rules or moves
3. Control system: decides which production
to apply next
– genetic programming, neural networks,
– ant intelligence, fuzzy logics,
– non-monotonic logics
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-28
Reasoning by Searching
• State Graph: All states and productions
• Search Tree: A record of state transitions
explored while searching for a goal state
– Breadth-first search
– Depth-first search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-29
A small portion of the eight-puzzle’s
state graph in backward reasoning
for breadth-first search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-30
A small portion of the eight-puzzle’s
state graph in backward reasoning
for depth-first search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-31
Deductive reasoning in the context of a
production system
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-32
An unsolved eight-puzzle
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-33
A sample search tree
- breadth-first search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-34
A sample search tree
- depth-first search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-35
Productions stacked for later
execution
- as a log
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-36
Heuristic Strategies
• Heuristic: A “rule of thumb” for making
decisions
• Requirements for good heuristics
– Must be easier to compute than a complete
solution
– Must provide a reasonable estimate of
proximity to a goal
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-37
An unsolved eight-puzzle
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-38
An algorithm for a control system
using heuristics
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-39
The beginnings of our heuristic
search
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-40
Figure 11.12 The search tree after
two passes
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-41
The search tree after three passes
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-42
The complete
search tree
formed by our
heuristic
system
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-43
Handling Real-World Knowledge
• Representation and storage
• Accessing relevant information
– Meta-Reasoning
– Closed-World Assumption
• Frame problem
– from animation
– how to move a table with the knowledge that
the glass on the table could fall and break.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-44
Learning
• Imitation
• Supervised Training
• Reinforcement
• Evolutionary Techniques
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-45
Artificial Neural Networks
• Artificial Neuron
– Each input is multiplied by a weighting factor.
– Output is 1 if sum of weighted inputs exceeds
the threshold value; 0 otherwise.
• Network is programmed by adjusting
weights using feedback from examples.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-47
A neuron in a living biological system
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley
Neural network configurations
11-49
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-50
The activities within a processing
unit
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-51
Representation of a processing unit
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-52
A neural network with two different
programs
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-53
An artificial neural network
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-54
Training an artificial neural network
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-55
Training an artificial neural network (continued)
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-56
Training an artificial neural network (continued)
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-57
Training an artificial neural network (continued)
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-58
The structure of ALVINN - Autonomous Land Vehicle in a Neural Net
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-59
Associative Memory
• Associative memory: The retrieval of
information relevant to the information at
hand
• One direction of research seeks to build
associative memory using neural networks
that when given a partial pattern, transition
themselves to a completed pattern.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-60
An artificial neural network
implementing an associative
memory
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-61
The steps leading to a stable
configuration
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-62
Robotics
• Truly autonomous robots require progress
in perception and reasoning.
• Major advances being made in mobility
• Plan development versus reactive
responses
• Evolutionary robotics
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley 11-63
Issues Raised by Artificial
Intelligence
• When should a computer’s decision be trusted over a human’s?
• If a computer can do a job better than a human, when should a human do the job anyway?
• What would be the social impact if computer “intelligence” surpasses that of many humans?