Artificial Intelligence: A Systems Approach

Front Cover
Jones & Bartlett Learning, Dec 26, 2008 - Computers - 498 pages
1 Review
This book offers students and AI programmers a new perspective on the study of artificial intelligence concepts. The essential topics and theory of AI are presented, but it also includes practical information on data input & reduction as well as data output (i.e., algorithm usage). Because traditional AI concepts such as pattern recognition, numerical optimization and data mining are now simply types of algorithms, a different approach is needed. This “sensor / algorithm / effecter” approach grounds the algorithms with an environment, helps students and AI practitioners to better understand them, and subsequently, how to apply them. The book has numerous up to date applications in game programming, intelligent agents, neural networks, artificial immune systems, and more. A CD-ROM with simulations, code, and figures accompanies the book.
  

What people are saying - Write a review

User Review - Flag as inappropriate

EA

Review: Artificial Intelligence: A Systems Approach, with CDROM

User Review  - Жанар Мамилина - Goodreads

comment Read full review

Related books

Selected pages

Contents

1 THE HISTORY OF AI
1
THE SEARCH FOR MECHANICAL INTELLIGENCE
2
THE VERY EARLY DAYS THE EARLY 1950s
3
AI Problem Solving and Games
4
ARTIFICIAL INTELLIGENCE EMERGES AS A FIELD
5
Building Tools for AI
6
Constrained Applications
7
AIS WINTER
8
LEASTMEANSQUARE LMS LEARNING
255
LMS Implementation
256
LEARNING WITH BACKPROPAGATION
258
Backpropagation Algorithm
260
Backpropagation Implementation
261
Tuning Backpropagation
267
PROBABILISTIC NEURAL NETWORKS PNN
268
PNN Algorithm
269

Additional Al Tools Emerge
9
AI REEMERGES
10
Agent Systems
12
SYSTEMS APPROACH
13
OVERVIEW OF THIS BOOK
15
Knowledge Representation
16
Neural Networks II
17
CHAPTER SUMMARY
18
EXERCISES
19
UNINFORMED SEARCH Chapter
21
CLASSES OF SEARCH
22
Search in a Puzzle Space
23
Search in an Adversarial Game Space
25
TREES GRAPHS AND REPRESENTATION
27
UNINFORMED SEARCH
29
Helper APIs
30
General Search Paradigms
31
Bidirectional Search
35
IMPROVEMENTS
38
ALGORITHM ADVANTAGES
39
REFERENCES
40
INFORMED SEARCH
42
BESTFIRST SEARCH BESTFS
43
BestFirst Search Implementation
45
Variants of BestFirst Search
49
A SEARCH
50
A Search and the Eight Puzzle
52
Search Implementation
54
Eight Puzzle Demonstration with A
57
A Variants
58
SIMULATED ANNEALING SA
59
The Traveling Salesman Problem TSP
61
Simulated Annealing Implementation
63
Simulated Annealing Demonstration
66
TABU SEARCH
68
Tabu Search Implementation
70
Tabu Search Demonstration
72
Tabu Search Variants
73
CONSTRAINT SATISFACTION PROBLEMS CSP
74
Scheduling as a CSP
76
CONSTRAINTSATISFACTION ALGORITHMS
77
MinConflicts Search
79
RESOURCES
80
AI AND GAMES
82
THE MINIMAX ALGORITHM
85
Minimax and TicTacToe
88
Minimax Implementation for TicTacToe
91
Minimax with AlphaBeta Pruning
94
CLASSICAL GAME AI
99
CheckerBoard Representation
100
Opening Books
101
Endgame Database
102
ChessBoard Representation
103
Minimax Search with AlphaBeta Pruning
104
Othello
105
Search Algorithm
106
Go
107
Opening Moves
108
Endgame
109
TDGammon
110
Poker
111
Loki A Learning Poker Player
112
Scrabble
113
VIDEO GAME AI
114
Applications of AI Algorithms in Video Games
115
Movement and Pathfinding
116
NPC Behavior
122
Static State Machines
123
Layered Behavior Architectures
124
Other ActionSelection Mechanisms
125
Coals and Plans
127
RealTime Strategy AI
129
CHAPTER SUMMARY
132
RESOURCES
133
EXERCISES
134
KNOWLEDGE REPRESENTATION
136
TYPES OF KNOWLEDGE
137
SEMANTIC NETWORKS
138
FRAMES
139
PROPOSITIONAL LOGIC
142
Deductive Reasoning with Propositional Logic
144
Limitations of Prepositional Logic
145
Atomic Sentences
146
Compound Sentences
147
Quantifiers
148
Information Retrieval and KR
150
Representing and Reasoning about an Environment
152
SEMANTIC WEB
156
COMPUTATIONAL KNOWLEDGE DISCOVERY
158
Automatic Mathematician AM
159
ONTOLOGY
160
COMMON SENSE
161
CHAPTER SUMMARY
162
EXERCISES
163
MACHINE LEARNING
164
Supervised Learning
165
Creating a Decision Tree
167
Characteristics of DecisionTree Learning
169
Markov Models
170
Word Generation with Markov Chains
172
Markov Chain Implementation
173
Other Applications of Markov Chains
177
Nearest Neighbor Classification
178
1NN Example
179
kNN Example
181
CHAPTER SUMMARY
185
EVOLUTIONARY COMPUTATION
188
Evolutionary Strategies
189
Evolutionary Programming
190
Genetic Programming
191
BIOLOGICAL MOTIVATION
192
GENETIC ALGORITHMS GA
193
Genetic Algorithm Implementation
197
GENETIC PROGRAMMING GP
205
Genetic Programming Implementation
208
EVOLUTIONARY STRATEGIES ES
213
Evolutionary Strategies Algorithm
214
Evolutionary Strategies Implementation
216
DIFFERENTIAL EVOLUTION DE
220
Differential Evolution Algorithm
221
Differential Evolution Implementation
223
PARTICLE SWARM OPTIMIZATION PSO
229
Particle Swarm Implementation
231
EVOLVABLE HARDWARE
237
REFERENCES
238
NEURAL NETWORKS I
242
BIOLOGICAL MOTIVATION
243
FUNDAMENTALS OF NEURAL NETWORKS
244
Single Layer Perceptrons SLPs
245
MultiLayer Perceptrons MLPs
247
Supervised vs Unsupervised Learning Algorithms
250
Perceptron Learning Algorithm
252
Perceptron Implementation
253
PNN Implementation
270
OTHER NEURAL NETWORK ARCHITECTURES
274
Recurrent Neural Network
276
Defining the Outputs
277
Number of Hidden Layers
278
NEURAL NETWORKS II
282
HEBBIAN LEARNING
283
Hebbs Rule
284
Hebb Rule Implementation
285
SIMPLE COMPETITIVE LEARNING
289
Vector Quantization
290
Vector Quantization Implementation
291
KMEANS CLUSTERING
297
kMeans Algorithm
298
kMeans Implementation
300
ADAPTIVE RESONANCE THEORY ART
306
ART1 Algorithm
307
ARTImplementation
309
HOPFIELD AUTOASSOCIATIVE MODEL
315
Hopfield AutoAssociator Algorithm
316
Hopfield Implementation
317
CHAPTER SUMMARY
320
REFERENCES
321
ROBOTICS AND AI
322
What is a Robot?
323
A Sampling from the Spectrum of Robotics
324
Taxonomy of Robotics
325
Fixed
326
Other Types of Robots
327
NATURAL SENSING AND CONTROL
329
PERCEPTION WITH SENSORS
330
ACTUATION WITH EFFECTORS
331
SIMPLE CONTROL ARCHITECTURES
332
Reactive Control
333
Other Control Systems
335
Cell Decomposition
336
Potential Fields
337
GROUP OR DISTRIBUTED ROBOTICS
338
ROBOT PROGRAMMING LANGUAGES
339
RESOURCES
340
INTELLIGENT AGENTS
342
ANATOMY OF AN AGENT
343
AGENT PROPERTIES AND AI
344
Rationale
345
Cooperative
346
AGENT TAXONOMIES
349
Virtual Character Agents
350
Entertainment Agents
351
ChatterBots
353
Mobile Agents
355
User Assistance Agent
357
Information Gathering and Filtering
358
Hybrid Agents
359
Types of Architectures
360
Deliberative Architectures
361
Blackboard Architectures
362
BeliefDesireIntention BDI Architecture
363
Hybrid Architectures
364
Architecture Descriptions
365
Behavior Networks Reactive Architecture
366
ATLANTIS Deliberative Architecture
368
Homer Deliberative Arch
369
BB1 Blackboard
370
Procedural Reasoning System BDI
371
Aglets Mobile
372
Messengers Mobile
373
Soar Hybrid
375
Aglets
376
Obliq
377
Traditional Languages
378
ACL FIPA Agent Communication Language
381
CHAPTER SUMMARY
382
REFERENCES
383
EXERCISES
384
BIOLOGICALLY INSPIRED AND HYBRID MODELS
386
OneDimensional CAs
387
TwoDimensional CAs
388
Conway Application
389
Turing Completeness
391
Touch points
393
Orchestrating Autonomic Managers
394
Autonomic Summary
395
Echo
396
The Bug or Agent
397
Variations of Artificial Life
401
FUZZY SYSTEMS
403
Fuzzy Logic Mapping
404
Fuzzy Logic Operators
407
Fuzzy Control
408
EVOLUTIONARY NEURAL NETWORKS
409
Simulated Evolution Example
412
ANT COLONY OPTIMIZATION AGO
416
Path Selection
418
Pheromone Evaporation
419
AGO Parameters
423
Synthesizing Emotion
424
RESOURCES
425
THE LANGUAGES OF AI
426
Functional Programming
427
Imperative Programming
430
ObjectOriented Programming OOP
431
Logic Programming
434
LANGUAGES OF AI
435
The LISP Language
436
Overview of the LISP Language
437
Predicates
438
Programs as Data
440
Functions in LISP
441
LISP Summary
444
History of Scheme
445
Predicates
446
List Processing
447
Conditions
448
Iteration and Maps
449
Procedures in Scheme
450
Scheme Summary
453
Predicates
454
Variables
455
Conditions
456
Iteration and Maps
457
Pattern Matching
458
POP11 Summary
461
History of Prolog
462
List Processing
463
Facts Rules and Evaluation
464
Arithmetic Expressions
471
Prolog Summary
473
CHAPTER SUMMARY
474
RESOURCES
475
ABOUT THE CDROM
478
INDEX
480
Copyright

Common terms and phrases

About the author (2008)

M. Tim Jones is a firmware architect with deep Hadoop and Pig experience. He's the author of "Artificial Intelligence: A Systems Approach", "GNU/Linux Application Programming", "AI Application Programming", "BSD Sockets Programming from a Multilanguage Perspective", and over 100 articles over a range of technical topics including Linux, Open-Source, Hadoop, the Hadoop ecosystem, and data science and visualization.

Bibliographic information