![Cover image for Hands-on AI with Java : smart gaming, robotics, and more Cover image for Hands-on AI with Java : smart gaming, robotics, and more](/client/assets/5.0.0/ctx//client/images/no_image.png)
Title:
Hands-on AI with Java : smart gaming, robotics, and more
Personal Author:
Publication Information:
New York : McGraw-Hill, 2004
ISBN:
9780071424967
Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000010064135 | QA76.73.J38 W574 2004 | Open Access Book | Book | Searching... |
Searching... | 30000010122062 | QA76.73.J38 W574 2004 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
Shows you how to give computer game characters, role-playing and decision-making skills. This book helps you: simulate evolution to find solutions to problems; develop machine-to-human text interactions for help desks, adventure games, computerized tutorials, and Web agents; and, guide machine tools for intelligent behavior.
Table of Contents
Acknowledgments | p. xi |
Chapter 1 Artificial intelligence | p. 1 |
Introduction | p. 2 |
Audience | p. 4 |
Purpose | p. 4 |
Examples | p. 4 |
Categories of Al | p. 5 |
Validation | p. 7 |
Statistics | p. 7 |
Validating Filtering and Predictive Systems | p. 8 |
Code: Strip Chart Display | p. 10 |
Validating Optimizations | p. 17 |
Validating Classification | p. 22 |
Code: Hinton Diagram Display | p. 28 |
And Beyond | p. 32 |
Chapter 2 Computing Framework | p. 33 |
Architecture Overview | p. 34 |
Software Agents | p. 40 |
Distributed Computing | p. 44 |
Networking | p. 44 |
Code: Threads | p. 48 |
Code: Pipes | p. 51 |
Code: Sockets | p. 53 |
Code: Class Loader | p. 56 |
Remote Method Invocation | p. 59 |
Communication Language | p. 60 |
Chapter 3 Control Systems | p. 63 |
Introduction: Reflexes | p. 64 |
Filtering | p. 65 |
Electronic RC Filters | p. 65 |
Convolution Filters | p. 66 |
Code: Convolution Filter | p. 68 |
Proportional-Integral-Derivative Control | p. 70 |
Code: Simplified Heater Process | p. 72 |
Fuzzy-Logic | p. 75 |
Crisp Boolean Logic | p. 75 |
Basic Fuzzy | p. 78 |
Code: Singleton Fuzzy Logic | p. 81 |
Code: Fuzzy Heater Controller | p. 89 |
Code: Fuzzy Logic | p. 94 |
Neural Reflexes | p. 101 |
Chapter 4 Scripted Behavior | p. 103 |
Data-Driven Intelligence | p. 104 |
Finite State Machines | p. 105 |
Designing an FSM | p. 106 |
Table Driven FSM | p. 108 |
Code: Table-Driven FSM | p. 110 |
Code: FSM Library | p. 113 |
Code: Coin Box Revisited | p. 124 |
Markov Models | p. 131 |
Code: Markov Sentence Generation | p. 136 |
Frame-Based Intelligence and Chatbots | p. 140 |
Pattern Matching | p. 141 |
Scripts | p. 143 |
Frames and Agendas | p. 143 |
Chapter 5 Discrete Searching | p. 145 |
Introduction | p. 146 |
Brute-Force Searching | p. 148 |
Depth-First | p. 148 |
Breadth-First | p. 149 |
Cheapest-First | p. 150 |
Bi-directional | p. 151 |
A* Search | p. 151 |
Code: A* Engine | p. 153 |
Code: A* Path Finding | p. 156 |
Code: A* Panel Nesting | p. 159 |
Two-Player Games | p. 162 |
Min-Max Search | p. 163 |
Alpha-Beta Pruning | p. 166 |
Code: Alpha-Beta Engine | p. 169 |
Code: Amoeba Game | p. 171 |
Chapter 6 Searching State Space | p. 175 |
What is State Space? | p. 176 |
Reinforcement Learning | p. 176 |
Core Concepts: Temporal Difference Learning | p. 177 |
SARSA | p. 180 |
Off-Policy Q-Learning | p. 182 |
Eligiblity Traces | p. 182 |
Code: Continuous Control | p. 184 |
Representing State Space | p. 188 |
Map Decompositions | p. 188 |
Partioning Continuous Space | p. 189 |
Genetic Algorithms | p. 192 |
Encoding the Problem | p. 193 |
Breeding | p. 200 |
Mutation | p. 203 |
Evalutating Fitness | p. 205 |
Selection | p. 207 |
Chapter 7 Thinking Logically | p. 209 |
Logic | p. 210 |
Zero Order | p. 210 |
First Order | p. 214 |
Second Order | p. 217 |
Using Logic | p. 218 |
Inference | p. 218 |
Proofs | p. 219 |
Unification | p. 222 |
Resolution | p. 223 |
Normalizing Sentences | p. 226 |
Proof by Resolution | p. 229 |
Code: Unifier | p. 230 |
Code: Backward Chaining | p. 237 |
Code: Forward Chaining | p. 242 |
Knowledge Representation | p. 245 |
Chapter 8 Supervised Neural Networks | p. 249 |
Simulated Intelligence | p. 250 |
Neural Models | p. 251 |
Biological Neurons | p. 251 |
Code: Hodgkin-Huxley Neural Model | p. 253 |
Pulsed Neuron Computing | p. 256 |
Computational Neurons | p. 258 |
Perceptron | p. 261 |
Code: Perceptron | p. 262 |
Multiple Categories | p. 264 |
Multi-Layer Perceptron | p. 264 |
State Space | p. 266 |
Delta Rule | p. 266 |
Backpropagation | p. 267 |
Code: Backpropagation Character Recognition | p. 271 |
Momentum | p. 279 |
Normalization | p. 281 |
Filtering | p. 282 |
Scaling | p. 282 |
Z-Axis Normalization | p. 283 |
Binary Representations | p. 284 |
Softmax | p. 285 |
Associative Memory | p. 286 |
Bidirectional Associative Memory | p. 286 |
Code: Hopfield Network | p. 287 |
Advanced Concepts | p. 289 |
Time-Series | p. 289 |
Fuzzy-Neural | p. 290 |
Growing Networks | p. 291 |
Chapter 9 Unsupervised Neural Networks | p. 293 |
Neurons Revisited | p. 294 |
Hebb | p. 294 |
Pattern Matching | p. 296 |
Self-Organizing Maps | p. 298 |
Basic Operation | p. 299 |
Code: RGB Map | p. 303 |
Network Variations | p. 308 |
Supervised | p. 308 |
Biologically Plausibility | p. 309 |
Growing Networks | p. 310 |
Elastic Networks for the Traveling Salesman Problem | p. 313 |
Code: Fast Elastic Net | p. 317 |
Document Processing | p. 321 |
Words | p. 321 |
Documents | p. 321 |
Hierarchy and Time | p. 322 |
Multi-Modal SOM | p. 323 |
Hierarchical SOM | p. 324 |
Time-Series | p. 326 |
References | p. 329 |
Index | p. 333 |