The subject of this book is predictive modular neural networks and their ap plication to time series problems: classification, prediction and identification. The intended audience is researchers and graduate students in the fields of neural networks, computer science, statistical pattern recognition, statistics, control theory and econometrics. Biologists, neurophysiologists and medical engineers may also find this book interesting. In the last decade the neural networks community has shown intense interest in both modular methods and time series problems. Similar interest has been expressed for many years in other fields as well, most notably in statistics, control theory, econometrics etc. There is a considerable overlap (not always recognized) of ideas and methods between these fields. Modular neural networks come by many other names, for instance multiple models, local models and mixtures of experts. The basic idea is to independently develop several "subnetworks" (modules), which may perform the same or re lated tasks, and then use an "appropriate" method for combining the outputs of the subnetworks. Some of the expected advantages of this approach (when compared with the use of "lumped" or "monolithic" networks) are: superior performance, reduced development time and greater flexibility. For instance, if a module is removed from the network and replaced by a new module (which may perform the same task more efficiently), it should not be necessary to retrain the aggregate network.
Erscheinungsdatum: 11.10.2012

lgrsnf/A:\compressed\10.1007%2F978-1-4615-5555-1.pdf

nexusstc/Predictive Modular Neural Networks: Applications to Time Series/2ecc1fdca58ae3dfaf87369086cc63b5.pdf

zlib/Engineering/Vassilios Petridis, Athanasios Kehagias (auth.)/Predictive Modular Neural Networks: Applications to Time Series_2092631.pdf

by Vassilios Petridis, Athanasios Kehagias

Petridis, Vassilios, Kehagias, Athanasios

The Springer International Series in Engineering and Computer Science -- 466, International series in engineering and computer science -- 466., Boston, MA, Massachusetts, 1998

Softcover reprint of the original 1st ed. 1998, 2012

United States, United States of America

Springer Nature, New York, NY, 2012

lg938753

{"edition":"1","isbns":["1461375401","1461555558","9781461375401","9781461555551"],"last_page":314,"publisher":"Springer US","series":"The Springer International Series in Engineering and Computer Science 466"}

Online full text is restricted to subscribers.
Also available in print.
Mode of access: World Wide Web.

Front Matter....Pages i-xi
Introduction....Pages 1-7
Front Matter....Pages 9-9
Premonn Classification and Prediction....Pages 11-38
Generalizations of the Basic Premonn....Pages 39-57
Mathematical Analysis....Pages 59-80
System Identification by the Predictive Modular Approach....Pages 81-97
Front Matter....Pages 99-99
Implementation Issues....Pages 101-107
Classification of Visually Evoked Responses....Pages 109-122
Prediction of Short Term Electric Loads....Pages 123-133
Parameter Estimation for and Activated Sludge Process....Pages 135-145
Front Matter....Pages 147-147
Source Identification Algorithms....Pages 149-172
Convergence of Parallel Data Allocation....Pages 173-207
Convergence of Serial Data Allocation....Pages 209-245
Front Matter....Pages 247-247
Bibliographic Remarks....Pages 249-266
Epilogue....Pages 267-269
Back Matter....Pages 271-314

This book presents a unified methodology for designing modular neural networks. A family of online algorithms for time series classification, prediction and identification are developed; and a rigorous mathematical analysis of their properties is provided. Case studies involving a number of real-world problems are also presented. Finally, an overview of the modular neural networks literature, including coverage of theoretical and experimental analysis, is provided. Predictive Modular Neural Networks: Applications to Time Series is an important reference work for engineers, computer scientists, and other researchers working in time series analysis, neural networks, control engineering, data mining and other intelligent and decision support areas. The book will also be of interest to researchers in biological and medical informatics.

2013-08-01