Evolving Connectionist Systems

This second edition of Evolving Connectionist Systems presents generic computational models and techniques that can be used for the development of evolving, adaptive modelling systems, as well as new trends including computational neuro-genetic modelling and quantum information processing related to evolving systems. New applications, such as autonomous robots, adaptive artificial life systems and adaptive decision support systems are also covered. The models and techniques used are connectionist-based and, where possible, existing connectionist models have been used and extended. Divided into four parts the book opens with evolving processes in nature; looks at methods and techniques that can be used in evolving connectionist systems; then covers various applications in bioinformatics and brain studies; finishing with applications for intelligent machines. Aimed at all those interested in developing adaptive models and systems to solve challenging real world problems in computer science and engineering.

Professor Nik Kasabov is the Founding Director and Chief Scientist of the Knowledge Engineering and Discovery Research Institute, Auckland, NZ. He holds a number of key positions, including Chair of the Adaptive Systems Task Force of the Neural Network Technical Committee of the IEEE. He has published extensively, and been Programme Chair of over 50 high-profile conferences.

Foreword I	p. vii
Foreword II	p. ix
Preface	p. xi
Abstract	p. xxi
Evolving Connectionist Methods	p. 1
Introduction	p. 3
Everything Is Evolving, but What Are the Evolving Rules?	p. 3
Evolving Intelligent Systems (EIS) and Evolving Connectionist Systems (ECOS)	p. 8
Biological Inspirations for EIS and ECOS	p. 11
About the Book	p. 13
Further Reading	p. 13
Feature Selection, Model Creation, and Model Validation	p. 15
Feature Selection and Feature Evaluation	p. 15
Incremental Feature Selection	p. 20
Machine Learning Methods - A Classification Scheme	p. 21
Probability and Information Measure. Bayesian Classifiers, Hidden Markov Models. Multiple Linear Regression	p. 35
Support Vector Machines (SVM)	p. 40
Inductive Versus Transductive Learning and Reasoning. Global, Local, and 'Personalised' Modelling	p. 44
Model Validation	p. 48
Exercise	p. 49
Summary and Open Problems	p. 49
Further Reading	p. 51
Evolving Connectionist Methods for Unsupervised Learning	p. 53
Unsupervised Learning from Data. Distance Measure	p. 53
Clustering	p. 57
Evolving Clustering Method (ECM)	p. 61
Vector Quantisation. SOM and ESOM	p. 68
Prototype Learning. ART	p. 73
Generic Applications of Unsupervised Learning Methods	p. 75
Exercise	p. 81
Summary and Open Problems	p. 81
Further Reading	p. 82
Evolving Connectionist Methods for Supervised Learning	p. 83
Connectionist Supervised Learning Methods	p. 83
Simple Evolving Connectionist Methods	p. 91
Evolving Fuzzy Neural Networks (EFuNN)	p. 97
Knowledge Manipulation in Evolving Fuzzy Neural Networks (EFuNNs) - Rule Insertion, Rule Extraction, Rule Aggregation	p. 109
Exercise	p. 124
Summary and Open Questions	p. 125
Further Reading	p. 126
Brain Inspired Evolving Connectionist Models	p. 127
State-Based ANN	p. 127
Reinforcement Learning	p. 132
Evolving Spiking Neural Networks	p. 133
Summary and Open Questions	p. 139
Further Reading	p. 140
Evolving Neuro-Fuzzy Inference Models	p. 141
Knowledge-Based Neural Networks	p. 141
Hybrid Neuro-Fuzzy Inference System (HyFIS)	p. 146
Dynamic Evolving Neuro-Fuzzy Inference Systems (DENFIS)	p. 149
Transductive Neuro-Fuzzy Inference Models	p. 161
Other Evolving Fuzzy Rule-Based Connectionist Systems	p. 168
Exercise	p. 175
Summary and Open Problems	p. 175
Further Reading	p. 175
Population-Generation-Based Methods: Evolutionary Computation	p. 177
A Brief Introduction to EC	p. 177
Genetic Algorithms and Evolutionary Strategies	p. 179
Traditional Use of EC for Learning and Optimisation in ANN	p. 183
EC for Parameter and Feature Optimisation of ECOS	p. 185
EC for Feature and Model Parameter Optimisation of Transductive Personalised (Nearest Neighbour) Models	p. 194
Particle Swarm Intelligence	p. 198
Artificial Life Systems (ALife)	p. 200
Exercise	p. 201
Summary and Open Questions	p. 202
Further Reading	p. 202
Evolving Integrated Multimodel Systems	p. 203
Evolving Multimodel Systems	p. 203
ECOS for Adaptive Incremental Data and Model Integration	p. 209
Integrating Kernel Functions and Regression Formulas in Knowledge-Based ANN	p. 215
Ensemble Learning Methods for ECOS	p. 219
Integrating ECOS and Evolving Ontologies	p. 225
Conclusion and Open Questions	p. 226
Further Reading	p. 227
Evolving Intelligent Systems	p. 229
Adaptive Modelling and Knowledge Discovery in Bioinformatics	p. 231
Bioinformatics: Information Growth, and Emergence of Knowledge	p. 231
DNA and RNA Sequence Data Analysis and Knowledge Discovery	p. 236
Gene Expression Data Analysis, Rule Extraction, and Disease Profiling	p. 242
Clustering of Time-Course Gene Expression Data	p. 259
Protein Structure Prediction	p. 262
Gene Regulatory Networks and the System Biology Approach	p. 265
Summary and Open Problems	p. 272
Further Reading	p. 273
Dynamic Modelling of Brain Functions and Cognitive Processes	p. 275
Evolving Structures and Functions in the Brain and Their Modelling	p. 275
Auditory, Visual, and Olfactory Information Processing and Their Modelling	p. 282
Adaptive Modelling of Brain States Based on EEG and fMRI Data	p. 290
Computational Neuro-Genetic Modelling (CNGM)	p. 295
Brain-Gene Ontology	p. 299
Summary and Open Problems	p. 301
Further Reading	p. 302
Modelling the Emergence of Acoustic Segments in Spoken Languages	p. 303
Introduction to the Issues of Learning Spoken Languages	p. 303
The Dilemma 'Innateness Versus Learning' or 'Nature Versus Nurture' Revisited	p. 305
ECOS for Modelling the Emergence of Phones and Phonemes	p. 307
Modelling Evolving Bilingual Systems	p. 316
Summary and Open Problems	p. 321
Further Reading	p. 323
Evolving Intelligent Systems for Adaptive Speech Recognition	p. 325
Introduction to Adaptive Speech Recognition	p. 325
Speech Signal Analysis and Speech Feature Selection	p. 329
Adaptive Phoneme-Based Speech Recognition	p. 331
Adaptive Whole Word and Phrase Recognition	p. 334
Adaptive, Spoken Language Human-Computer Interfaces	p. 338
Exercise	p. 339
Summary and Open Problems	p. 339
Further Reading	p. 340
Evolving Intelligent Systems for Adaptive Image Processing	p. 341
Image Analysis and Feature Selection	p. 341
Online Colour Quantisation	p. 344
Adaptive Image Classification	p. 348
Incremental Face Membership Authentication and Face Recognition	p. 350
Online Video-Camera Operation Recognition	p. 353
Exercise	p. 357
Summary and Open Problems	p. 358
Further Reading	p. 358
Evolving Intelligent Systems for Adaptive Multimodal Information Processing	p. 361
Multimodal Information Processing	p. 361
Adaptive, Integrated, Auditory and Visual Information Processing	p. 362
Adaptive Person Identification Based on Integrated Auditory and Visual Information	p. 364
Person Verification Based on Auditory and Visual Information	p. 373
Summary and Open Problems	p. 379
Further Reading	p. 380
Evolving Intelligent Systems for Robotics and Decision Support	p. 381
Adaptive Learning Robots	p. 381
Modelling of Evolving Financial and Socioeconomic Processes	p. 382
Adaptive Environmental Risk of Event Evaluation	p. 385
Summary and Open Questions	p. 390
Further Reading	p. 391
What Is Next: Quantum Inspired Evolving Intelligent Systems?	p. 393
Why Quantum Inspired EIS?	p. 393
Quantum Information Processing	p. 394
Quantum Inspired Evolutionary Optimisation Techniques	p. 396
Quantum Inspired Connectionist Systems	p. 398
Linking Quantum to Neuro-Genetic Information Processing: Is This The Challenge For the Future?	p. 400
Summary and Open Questions	p. 402
Further Reading	p. 403
A Sample Program in MATLAB for Time-Series Analysis	p. 405
A Sample MATLAB Program to Record Speech and to Transform It into FFT Coefficients as Features	p. 407
A Sample MATLAB Program for Image Analysis and Feature Extraction	p. 411
Macroeconomic Data Used in Section 14.2 (Chapter 14)	p. 415
References	p. 417
Extended Glossary	p. 439
Index	p. 453
Table of Contents provided by Ingram. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.