Genetic Programming Theory and Practice IV (eBook)

Contents 6
Contributing Authors 9
Preface 13
Foreword 15
Chapter 1 GENETIC PROGRAMMING: THEORY AND PRACTICE An Introduction to Volume IV 17
1. Theory and Practice: Crossing a Watershed 17
2. Common Themes 18
3. Common Applications 19
4. Common Hurdles 20
5. Improving GP: convergence of practice and theory 21
6. Next Steps 26
Chapter 2 GENOME- WIDE GENETIC ANALYSIS USING GENETIC PROGRAMMING: THE CRITICAL NEED FOR EXPERT KNOWLEDGE 27
1. Introduction 28
2. Genetic Programming Methods 31
3. Multifactor Dimensionality Reduction ( MDR) for Attribute Construction 34
4. Expert Knowledge from T/ ined ReliefF 34
5. Data Simulation and Analysis 35
6. Experimental Results 36
7. Discussion and Conclusion 36
8. Acknowledgment 41
References 41
Chapter 3 LIFTING THE CURSE OF DIMENSIONALITY 45
1. Introduction 45
2. Statement of Problem 46
3. Methods 46
4. Concentrating the Data 48
5. Testing for Generality 51
6. Discussion 52
7. Summary 54
References 55
Chapter 4 GENETIC PROGRAMMING FOR CLASSIFYING CANCER DATA AND CONTROLLING HUMANOID ROBOTS 57
1. Introduction 57
2. Classification of Gene Expression Data GP- based classification 59
3. Evolutionary Humanoid Robots 64
4. Conclusion 70
Chapter 5 BOOSTING IMPROVES STABILITY AND ACCURACY OF GENETIC PROGRAMMING IN BIOLOGICAL SEQUENCE CLASSIFICATION 76
1. Introduction 76
2. Methods Genetic programming with string queries 77
3. Results Predicting microRNA targets 81
4. Discussion 90
References 91
Chapter 6 ORTHOGONAL EVOLUTION OF TEAMS: A CLASS OF ALGORITHMS FOR EVOLVING TEAMS WITH INVERSELY CORRELATED ERRORS 94
1. Introduction 94
2. Background 96
3. Orthogonal Evolution of Teams 99
4. Experiments 100
5. Conclusions 107
References 108
Chapter 7 MULTIDIMENSIONAL TAGS, COOPERATIVE POPULATIONS, AND GENETIC PROGRAMMING 111
1. Cooperation and adaptive complexity 111
2. Tag- mediated cooperation 112
3. Multidimensional tags 113
4. Results 115
5. Discussion 118
6. Cooperation and genetic programming 121
7. Conclusions 123
Acknowledgments 123
References 123
Chapter 8 COEVOLVING FITNESS MODELS FOR ACCELERATING EVOLUTION AND REDUCING EVALUATIONS 127
1. Introduction 127
2. Preliminaries Coevolution 128
3. Coevolved Fitness Models 131
4. Training Data Sample Fitness Model 134
5. Experiments in Symbolic Regression 135
6. Conclusion 140
References 141
Chapter 9 MULTI- DOMAIN OBSERVATIONS CONCERNING THE USE OF GENETIC PROGRAMMING TO AUTOMATICALLY SYNTHESIZE HUMAN-COMPETITIVE DESIGNS FOR ANALOG CIRCUITS, OPTICAL LENS SYSTEMS, CONTROLLERS, ANTENNAS, MECHANICAL SYSTEMS, AND QUANTUM COMPUTING CIRCUITS 145
1. Introduction 146
2. Background on genetic programming and developmental genetic programming 146
3. Cross- domain common features of human- competitive results produced by genetic programming 147
4. Amenability of a domain to the application of genetic programming to automated design 154
5. Genetic or evolutionary search domain- specific specializations 156
6, Techniques issues observed in multiple domains 156
7. Conclusions 158
References 158
Chapter 10 ROBUST PARETO FRONT GENETIC PROGRAMMING PARAMETER SELECTION BASED ON DESIGN OF EXPERIMENTS AND INDUSTRIAL DATA 162
1. Introduction 162
2. Key Parameters of Pareto Front Genetic Programming for Symbolic Regression 164
3. A Generic Methodology for Optimal GP Parameter Selection Based On Statistical Design of Experiments 166
4. Results Experimental Setup 168
5. Robustness 174
6. Summary 177
References 177
Chapter 11 PURSUING THE PARETO PARADIGM: TOURNAMENTS, ALGORITHM VARIATIONS AND ORDINAL OPTIMIZATION 180
1. Introduction 180
2. Pareto- Aware GP - Variations on the Pareto Theme 181
3. Tournament Selection Intensity - Single and Multiple Winners with One Objective 185
4. Tunable Pareto- Aware Selection Strategies 189
5. Ordinal Optimization and Application to Symbolic Regression 193
6. Conclusions and Summary 197
References 197
Chapter 12 APPLYING GENETIC PROGRAMMING TO RESERVOIR HISTORY MATCHING PROBLEM 199
1. Introduction 200
2. Reservoir History Matching Problem 200
3. A Genetic Programming Solution 203
4. A Case Study 204
5. Concluding Remarks 211
Acknowledgment 212
References 212
Chapter 13 COMPARISON OF ROBUSTNESS OF THREE FILTER DESIGN STRATEGIES USING GENETIC PROGRAMMING AND BOND GRAPHS 214
1. Introduction 215
2. Related Work 216
3. Analog Filter Synthesis Using Bond Graphs and Genetic Programming Bond Graphs 217
4. Evolving Robust Analog Filters with Components of Preferred Values Using Bond Graphs and Evolutionary Algorithms 222
5. Experiments and Results 223
6. Conclusions and Future Work 227
References 227
Chapter 14 DESIGN OF POSYNOMIAL MODELS FOR MOSFETS: SYMBOLIC REGRESSION USING GENETIC ALGORITHMS 229
1. Introduction 229
2. Geometric Programming 233
3. The MOS Posynomial Modeling Problem 236
4. Our Genetic Algorithm for MOS Modeling 237
5. Experiments 240
6. Summary 243
7. Future Work 244
Acknowledgements 244
References 244
Chapter 15 PHASE TRANSITIONS IN GENETIC PROGRAMMING SEARCH 247
1. Introduction 247
2. Transitions in GP Search Background 248
3. Methods and Tools 253
4. Case Study 255
5. Discussion 260
6. Conclusions 262
7. Acknowledgements 262
References 263
Chapter 16 EFFICIENT MARKOV CHAIN MODEL OF MACHINE CODE PROGRAM EXECUTION AND HALTING 267
1. Introduction 267
2. The T7 computer 269
3. Markov chain model: States 270
4. Markov chain model: transition probabilities 271
5. Halting probability 277
6. Efficient formulations of the model 278
7. Discussion Implications for Genetic Programming Research 283
8. Conclusions 286
References 287
Chapter 17 A RE- EXAMINATION OF A REAL WORLD BLOOD FLOW MODELING PROBLEM USING CONTEXT- AWARE CROSSOVER 289
1. Introduction 289
2. Background 290
3. Context- aware crossover for GP 292
4. Blood Flow Modeling problem 299
5. Conclusion & Future Work
References 307
Chapter 18 LARGE- SCALE, TIME- CONSTRAINED SYMBOLIC REGRESSION 309
1. Introduction 309
Summary 323
Acknowledgments 324
References 324
Chapter 19 STOCK SELECTION: AN INNOVATIVE APPLICATION OF GENETIC PROGRAMMING METHODOLOGY 325
1. Introduction 326
2. Financial Data 327
3. Genetic Programming Methodology Overview 328
4. Stock Selection Models Variables and Factors 332
5. Results and Discussion Statistical Test 336
6. Conclusion 341
7. Acknowledgements 343
Notes 343
References 343
Index 345