Contents

part one Foundations

chapter one　Models and Concepts of Life and Intelligence　3

The Mechanics of Life and Thought　4

Stochastic Adaptation: Is Anything Ever Really Random"para" label-module="para">

The “Two Great Stochastic Systems”　12

The Game of Life: Emergence in Complex Systems　16

The Game of Life　17

Emergence　18

Cellular Automata and the Edge of Chaos　20

Artificial Life in Computer Programs　26

Intelligence: Good Minds in People and Machines　30

Intelligence in People: The Boring Criterion　30

Intelligence in Machines: The Turing Criterion　32

chapter two　Symbols, Connections, and Optimization by Trial and Error　35

Symbols in Trees and Networks　36

Problem Solving and Optimization　48

A Super-Simple Optimization Problem　49

Three Spaces of Optimization　51

Fitness Landscapes　52

High-Dimensional Cognitive Space and Word Meanings　55

Two Factors of Complexity: NK Landscapes　60

Combinatorial Optimization　64

Binary Optimization　67

Random and Greedy Searches　71

Hill Climbing　72

Simulated Annealing　73

Binary and Gray Coding　74

Step Sizes and Granularity　75

Optimizing with Real Numbers　77

Summary　78

chapter three　On Our Nonexistence as Entities: The Social Organism　81

Views of Evolution　82

Gaia: The Living Earth　83

Differential Selection　86

Our Microscopic Masters"para" label-module="para">

Looking for the Right Zoom Angle　92

Flocks, Herds, Schools, and Swarms: Social Behavior as Optimization　94

Accomplishments of the Social Insects　98

Optimizing with Simulated Ants: Computational Swarm Intelligence　105

Staying Together but Not Colliding: Flocks, Herds, and Schools　109

Robot Societies　115

Shallow Understanding　125

Agency　129

Summary　131

chapter four　Evolutionary Computation Theory and Paradigms　133

Introduction　134

Evolutionary Computation History　134

The Four Areas of Evolutionary Computation　135

Genetic Algorithms　135

Evolutionary Programming　139

Evolution Strategies　140

Genetic Programming　141

Toward Unification　141

Evolutionary Computation Overview　142

EC Paradigm Attributes　142

Implementation　143

Genetic Algorithms　146

An Overview　146

A Simple GA Example Problem　147

A Review of GA Operations　152

Schemata and the Schema Theorem　159

Final Comments on Genetic Algorithms　163

Evolutionary Programming　164

The Evolutionary Programming Procedure　165

Finite State Machine Evolution　166

Function Optimization　169

Final Comments　171

Evolution Strategies　172

Mutation　172

Recombination　174

Selection　175

Genetic Programming　179

Summary　185

chapter five　Humans—Actual, Imagined, and Implied　187

Studying Minds　188

The Fall of the Behaviorist Empire　193

The Cognitive Revolution　195

Bandura’s Social Learning Paradigm　197

Social Psychology　199

Lewin’s Field Theory　200

Norms, Conformity, and Social Influence　202

Sociocognition　205

Simulating Social Influence　206

Paradigm Shifts in Cognitive Science　210

The Evolution of Cooperation　214

Explanatory Coherence　216

Networks in Groups　218

Culture in Theory and Practice　220

Coordination Games　223

The El Farol Problem　226

Sugarscape　229

Tesfatsion’s ACE　232

Picker’s Competing-Norms Model　233

Latané’s Dynamic Social Impact Theory　235

Boyd and Richerson’s Evolutionary Culture Model　240

Memetics　245

Memetic Algorithms　248

Cultural Algorithms　253

Convergence of Basic and Applied Research　254

Culture—and Life without It　255

Summary　258

chapter six　Thinking Is Social　261

Introduction　262

Adaptation on Three Levels　263

The Adaptive Culture Model　263

Axelrod’s Culture Model　265

Experiment One: Similarity in Axelrod’s Model　267

Experiment Two: Optimization of an Arbitrary Function　268

Experiment Three: A Slightly Harder and More Interesting Function　269

Experiment Four: A Hard Function　271

Experiment Five: Parallel Constraint Satisfaction　273

Experiment Six: Symbol Processing　279

Discussion　282

Summary　284

part two　The Particle Swarm and Collective Intelligence

chapter seven　The Particle Swarm　287

Sociocognitive Underpinnings: Evaluate, Compare, and Imitate　288

Evaluate　288

Compare　288

Imitate　289

A Model of Binary Decision　289

Testing the Binary Algorithm with the De Jong Test Suite　297

No Free Lunch　299

Multimodality　302

Minds as Parallel Constraint Satisfaction Networks in Cultures　307

The Particle Swarm in Continuous Numbers　309

The Particle Swarm in Real-Number Space　309

Pseudocode for Particle Swarm Optimization in Continuous Numbers　313

Implementation Issues　314

An Example: Particle Swarm Optimization of Neural Net Weights　314

A Real-World Application　318

The Hybrid Particle Swarm　319

Science as Collaborative Search　320

Emergent Culture, Immergent Intelligence　323

Summary　324

chapter eight　Variations and Comparisons　327

Variations of the Particle Swarm Paradigm　328

Parameter Selection　328

Controlling the Explosion　337

Particle Interactions　342

Neighborhood Topology　343

Substituting Cluster Centers for Previous Bests　347

Adding Selection to Particle Swarms　353

Comparing Inertia Weights and Constriction Factors　354

Asymmetric Initialization　357

Some Thoughts on Variations　359

Are Particle Swarms Really a Kind of Evolutionary Algorithm"para" label-module="para">

Evolution beyond Darwin　362

Selection and Self-Organization　363

Ergodicity: Where Can It Get from Here"para" label-module="para">

Convergence of Evolutionary Computation and Particle Swarms　367

Summary　368

chapter nine　Applications　369

Evolving Neural Networks with Particle Swarms　370

Review of Previous Work　370

Advantages and Disadvantages of Previous Approaches　374

The Particle Swarm Optimization Implementation Used Here　376

Implementing Neural Network Evolution　377

An Example Application　379

Conclusions　381

Human Tremor Analysis　382

Data Acquisition Using Actigraphy　383

Data Preprocessing　385

Analysis with Particle Swarm Optimization　386

Summary　389

Other Applications　389

Computer Numerically Controlled Milling Optimization　389

Ingredient Mix Optimization　391

Reactive Power and Voltage Control　391

Battery Pack State-of-Charge Estimation　391

Summary　392

chapter ten　Implications and Speculations　393

Introduction　394

Assertions　395

Up from Social Learning: Bandura　398

Information and Motivation　399

Vicarious versus Direct Experience　399

The Spread of Influence　400

Machine Adaptation　401

Learning or Adaptation"para" label-module="para">

Cellular Automata　403

Down from Culture　405

Soft Computing　408

Interaction within Small Groups: Group Polarization　409

Informational and Normative Social Influence　411

Self-Esteem　412

Self-Attribution and Social Illusion　414

Summary　419

chapter eleven　And in Conclusion . . .　421

Appendix A Statistics for Swarmers　429

Appendix B Genetic Algorithm Implementation　451

Glossary　457

References　475

Index　4972100433B