Muutke küpsiste eelistusi

E-raamat: Evolving Connectionist Systems: The Knowledge Engineering Approach

  • Formaat: PDF+DRM
  • Ilmumisaeg: 23-Aug-2007
  • Kirjastus: Springer London Ltd
  • Keel: eng
  • ISBN-13: 9781846283475
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 159,93 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Evolving Connectionist Systems: The Knowledge Engineering ApproachSuurem pilt
  • Formaat: PDF+DRM
  • Ilmumisaeg: 23-Aug-2007
  • Kirjastus: Springer London Ltd
  • Keel: eng
  • ISBN-13: 9781846283475
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

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.

This second edition of the must-read work in the field presents generic computational models and techniques that can be used for the development of evolving, adaptive modeling systems, as well as new trends including computational neuro-genetic modeling 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.
Foreword I by Walter J. Freeman vii
Foreword II by John G. Taylor ix
Preface xi
Abstract xxi
Part I Evolving Connectionist Methods 1
Introduction
3
I.1 Everything Is Evolving, but What Are the Evolving Rules?
3
I.2 Evolving Intelligent Systems (EIS) and Evolving Connectionist Systems (EGOS)
8
I.3 Biological Inspirations for EIS and EGOS
11
I.4 About the Book
13
I.5 Further Reading
13
1 Feature Selection, Model Creation, and Model Validation
15
1.1 Feature Selection and Feature Evaluation
15
1.2 Incremental Feature Selection
20
1.3 Machine Learning Methods - A Classification Scheme
21
1.4 Probability and Information Measure. Bayesian Classifiers, Hidden Markov Models. Multiple Linear Regression
35
1.5 Support Vector Machines (SVM)
40
1.6 Inductive Versus Transductive Learning and Reasoning. Global, Local, and 'Personalised' Modelling
44
1.7 Model Validation
48
1.8 Exercise
49
1.9 Summary and Open Problems
49
1.10 Further Reading
51
2 Evolving Connectionist Methods for Unsupervised Learning
53
2.1 Unsupervised Learning from Data. Distance Measure
53
2.2 Clustering
57
2.3 Evolving Clustering Method (ECM)
61
2.4 Vector Quantisation. SOM and ESOM
68
2.5 Prototype Learning. ART
73
2.6 Generic Applications of Unsupervised Learning Methods
75
2.7 Exercise
81
2.8 Summary and Open Problems
81
2.9 Further Reading
82
3 Evolving Connectionist Methods for Supervised Learning
83
3.1 Connectionist Supervised Learning Methods
83
3.2 Simple Evolving Connectionist Methods
91
3.3 Evolving Fuzzy Neural Networks (EFuNN)
97
3.4 Knowledge Manipulation in Evolving Fuzzy Neural Networks (EFuNNs) - Rule Insertion, Rule Extraction, Rule Aggregation
109
3.5 Exercise
124
3.6 Summary and Open Questions
125
3.7 Further Reading
126
4 Brain Inspired Evolving Connectionist Models
127
4.1 State-Based ANN
127
4.2 Reinforcement Learning
132
4.3 Evolving Spiking Neural Networks
133
4.4 Summary and Open Questions
139
4.5 Further Reading
140
5 Evolving Neuro-Fuzzy Inference Models
141
5.1 Knowledge-Based Neural Networks
141
5.2 Hybrid Neuro-Fuzzy Inference System (HyFIS)
146
5.3 Dynamic Evolving Neuro-Fuzzy Inference Systems (DENFIS)
149
5.4 Transductive Neuro-Fuzzy Inference Models
161
5.5 Other Evolving Fuzzy Rule-Based Connectionist Systems
168
5.6 Exercise
175
5.7 Summary and Open Problems
175
5.8 Further Reading
175
6 Population-Generation-Based Methods: Evolutionary Computation
177
6.1 A Brief Introduction to EC
177
6.2 Genetic Algorithms and Evolutionary Strategies
179
6.3 Traditional Use of EC for Learning and Optimisation in ANN
183
6.4 EC for Parameter and Feature Optimisation of EGOS
185
6.5 EC for Feature and Model Parameter Optimisation of Transductive Personalised (Nearest Neighbour) Models
194
6.6 Particle Swarm Intelligence
198
6.7 Artificial Life Systems (ALife)
200
6.8 Exercise
201
6.9 Summary and Open Questions
202
6.10 Further Reading
202
7 Evolving Integrated Multimodel Systems
203
7.1 Evolving Multimodel Systems
203
7.2 EGOS for Adaptive Incremental Data and Model Integration
209
7.3 Integrating Kernel Functions and Regression Formulas in Knowledge-Based ANN
215
7.4 Ensemble Learning Methods for EGOS
219
7.5 Integrating EGOS and Evolving Ontologies
225
7.6 Conclusion and Open Questions
226
7.7 Further Reading
227
Part II Evolving Intelligent Systems 229
8 Adaptive Modelling and Knowledge Discovery in Bioinformatics
231
8.1 Bioinformatics: Information Growth, and Emergence of Knowledge
231
8.2 DNA and RNA Sequence Data Analysis and Knowledge Discovery
236
8.3 Gene Expression Data Analysis, Rule Extraction, and Disease Profiling
242
8.4 Clustering of Time-Course Gene Expression Data
259
8.5 Protein Structure Prediction
262
8.6 Gene Regulatory Networks and the System Biology Approach
265
8.7 Summary and Open Problems
272
8.8 Further Reading
273
9 Dynamic Modelling of Brain Functions and Cognitive Processes
275
9.1 Evolving Structures and Functions in the Brain and Their Modelling
275
9.2 Auditory, Visual, and Olfactory Information Processing and Their Modelling
282
9.3 Adaptive Modelling of Brain States Based on EEG and fMRI Data
290
9.4 Computational Neuro-Genetic Modelling (CNGM)
295
9.5 Brain-Gene Ontology
299
9.6 Summary and Open Problems
301
9.7 Further Reading
302
10 Modelling the Emergence of Acoustic Segments in Spoken Languages
303
10.1 Introduction to the Issues of Learning Spoken Languages
303
10.2 The Dilemma 'Innateness Versus Learning' or 'Nature Versus Nurture' Revisited
305
10.3 EGOS for Modelling the Emergence of Phones and Phonemes
307
10.4 Modelling Evolving Bilingual Systems
316
10.5 Summary and Open Problems
321
10.6 Further Reading
323
11 Evolving Intelligent Systems for Adaptive Speech Recognition
325
11.1 Introduction to Adaptive Speech Recognition
325
11.2 Speech Signal Analysis and Speech Feature Selection
329
11.3 Adaptive Phoneme-Based Speech Recognition
331
11.4 Adaptive Whole Word and Phrase Recognition
334
11.5 Adaptive, Spoken Language Human-Computer Interfaces
338
11.6 Exercise
339
11.7 Summary and Open Problems
339
11.8 Further Reading
340
12 Evolving Intelligent Systems for Adaptive Image Processing
341
12.1 Image Analysis and Feature Selection
341
12.2 Online Colour Quantisation
344
12.3 Adaptive Image Classification
348
12.4 Incremental Face Membership Authentication and Face Recognition
350
12.5 Online Video-Camera Operation Recognition
353
12.6 Exercise
357
12.7 Summary and Open Problems
358
12.8 Further Reading
358
13 Evolving Intelligent Systems for Adaptive Multimodal Information Processing
361
13.1 Multimodal Information Processing
361
13.2 Adaptive, Integrated, Auditory and Visual Information Processing
362
13.3 Adaptive Person Identification Based on Integrated Auditory and Visual Information
364
13.4 Person Verification Based on Auditory and Visual Information
373
13.5 Summary and Open Problems
379
13.6 Further Reading
380
14 Evolving Intelligent Systems for Robotics and Decision Support
381
14.1 Adaptive Learning Robots
381
14.2 Modelling of Evolving Financial and Socioeconomic Processes
382
14.3 Adaptive Environmental Risk of Event Evaluation
385
14.4 Summary and Open Questions
390
14.5 Further Reading
391
15 What Is Next: Quantum Inspired Evolving Intelligent Systems?
393
15.1 Why Quantum Inspired EIS?
393
15.2 Quantum Information Processing
394
15.3 Quantum Inspired Evolutionary Optimisation Techniques
396
15.4 Quantum Inspired Connectionist Systems
398
15.5 Linking Quantum to Neuro-Genetic Information Processing: Is This The Challenge For the Future?
400
15.6 Summary and Open Questions
402
15.7 Further Reading
403
Appendix A. A Sample Program in MATLAB for Time-Series Analysis 405
Appendix B. A Sample MATLAB Program to Record Speech and to Transform It into FFT Coefficients as Features 407
Appendix C. A Sample MATLAB Program for Image Analysis and Feature Extraction 411
Appendix D. Macroeconomic Data Used in Section 14.2 (Chapter 14) 415
References 417
Extended Glossary 439
Index 453


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.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97818462834752e.html
Märksõnad: