Recurrent Neural Networks for Prediction
Learning Algorithms, Architectures and Stability

Danilo P. Mandic (Author), Jonathon A. Chambers (Author)

9780471495178, Wiley

Hardback, published 6 August 2001

304 pages
24.7 x 17.4 x 2.3 cm, 0.709 kg

Durch die Anwendung rückbezüglicher neuronaler Netze läßt sich die Leistungsfähigkeit konventioneller Technologien der digitalen Datenverarbeitung signifikant erhöhen. Von besonderer Bedeutung ist dies für komplexe Aufgaben, wie z.B. die mobile Kommunikation, die Robotik und die Medizintechnik. Das Buch faßt Originalarbeiten zur Stabilität neuronaler Netze zusammen und verbindet streng mathematische Analysen mit anschaulichen Anwendungen und experimentellen Belegen.

Preface.

Introduction.

Fundamentals.

Network Architectures for Prediction.

Activation Functions Used in Neural Networks.

Recurrent Neural Networks Architectures.

Neural Networks as Nonlinear Adaptive Filters.

Stability Issues in RNN Architectures.

Data-Reusing Adaptive Learning Algorithms.

A Class of Normalised Algorithms for Online Training of Recurrent Neural Networks.

Convergence of Online Learning Algorithms in Neural Networks.

Some Practical Considerations of Predictability and Learning Algorithms for Various Signals.

Exploiting Inherent Relationships Between Parameters in Recurrent Neural Networks.

Appendix A: The O Notation and Vector and Matrix Differentiation.

Appendix B: Concepts from the Approximation Theory.

Appendix C: Complex Sigmoid Activation Functions, Holomorphic Mappings and Modular Groups.

Appendix D: Learning Algorithms for RNNs.

Appendix E: Terminology Used in the Field of Neural Networks.

Appendix F: On the A Posteriori Approach in Science and Engineering.

Appendix G: Contraction Mapping Theorems.

Appendix H: Linear GAS Relaxation.

Appendix I: The Main Notions in Stability Theory.

Appendix J: Deasonsonalising Time Series.

References.

Index.

Subject Areas: Electronics & communications engineering [TJ]