Advertisement

Supervised Learning with Complex-valued Neural Networks

  • Sundaram Suresh
  • Narasimhan Sundararajan
  • Ramasamy Savitha

Part of the Studies in Computational Intelligence book series (SCI, volume 421)

Table of contents

  1. Front Matter
    Pages 1-19
  2. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 1-29
  3. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 31-47
  4. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 49-71
  5. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 73-83
  6. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 85-107
  7. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 109-123
  8. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 125-133
  9. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages 135-168
  10. Sundaram Suresh, Narasimhan Sundararajan, Ramasamy Savitha
    Pages E1-E1

About this book

Introduction

Recent advancements in the field of telecommunications, medical imaging and signal processing deal with signals that are inherently time varying, nonlinear and complex-valued. The time varying, nonlinear characteristics of these signals can be effectively analyzed using artificial neural networks.  Furthermore, to efficiently preserve the physical characteristics of these complex-valued signals, it is important to develop complex-valued neural networks and derive their learning algorithms to represent these signals at every step of the learning process. This monograph comprises a collection of new supervised learning algorithms along with novel architectures for complex-valued neural networks. The concepts of meta-cognition equipped with a self-regulated learning have been known to be the best human learning strategy. In this monograph, the principles of meta-cognition have been introduced for complex-valued neural networks in both the batch and sequential learning modes. For applications where the computation time of the training process is critical, a fast learning complex-valued neural network called as a fully complex-valued relaxation network along with its learning algorithm has been presented. The presence of orthogonal decision boundaries helps complex-valued neural networks to outperform real-valued networks in performing classification tasks. This aspect has been highlighted. The performances of various complex-valued neural networks are evaluated on a set of benchmark and real-world function approximation and real-valued classification problems.

Keywords

Adaptive Beam-Forming Batch/Sequential Learning Complex-Valued Multi-Layer Perception Complex-Valued Radial Basis Function Network Fast Learning Algorithm Meta-Cognition Quadrature Amplitude Modulation Real-Valued Classification

Authors and affiliations

  • Sundaram Suresh
    • 1
  • Narasimhan Sundararajan
    • 2
  • Ramasamy Savitha
    • 3
  1. 1.School of Computer EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.School of Electrical and Electronics EnNanyang Technological UniversitySingaporeSingapore
  3. 3.School of Computer EngineeringNanyang Technological UniversitySingaporeSingapore

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-642-29491-4
  • Copyright Information Springer-Verlag GmbH Berlin Heidelberg 2013
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Engineering
  • Print ISBN 978-3-642-29490-7
  • Online ISBN 978-3-642-29491-4
  • Series Print ISSN 1860-949X
  • Series Online ISSN 1860-9503
  • Buy this book on publisher's site
Industry Sectors
Pharma
Automotive
Chemical Manufacturing
Biotechnology
Finance, Business & Banking
Electronics
IT & Software
Telecommunications
Energy, Utilities & Environment
Aerospace
Oil, Gas & Geosciences
Engineering