Advertisement

Introduction

  • Cornelia Denz
Chapter
  • 168 Downloads

Abstract

What have optics to do with mathematical algorithms for neural networks? In order to compute, we need to transport data from place to place, connect components together, store data and be able to switch on and off. All these features seem to be realized in an easy way by electronic components as there are wires or conducting pathways on silicon, electrical junctions, a memory and the transistor. However, for the purpose of neural networks, there are many practical difficulties in implementation. The most obvious of these is that neural networks require by their nature an adaptive feature, which means that they are able to distinguish between states and change their decision rules themselves as necessary. It is very difficult to implement such a feature in integrated circuit technology. Moreover, the high interconnectivity also demands a lot of effort in electronics.

Keywords

Input Pattern Biological Neural Network Integrate Circuit Technology High Interconnectivity Simple Processing Element 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Further Reading

  1. 1.
    R. Beale, T. Jackson, Neural Computing: An Introduction, A. Hilger, Bristol (1992). An instructive, detailed and easy-to-read introduction into the field. Many of the concepts in the first two chapters of this book originate from that introduction.Google Scholar
  2. 2.
    P.D. Wasserman, Neural Computing: Theory and Practice, Chapman & Hall (1989). A well-written introduction with a lot of examples.Google Scholar
  3. 3.
    R.P. Lippmann, An Introduction to Computing with Neural Nets, IEEE ASSP Magazine, April 1987. An excellent and compact overview of the whole area. The mathematical algorithms in that book have been formulated following the instructions in that paper.Google Scholar
  4. 4.
    J.L. McClelland, D.E. Rumelhardt, Parallel Distributed Processing, Vol. 1–3, MIT Press (1986). This book covers the foundations and many of the current approaches and models.Google Scholar
  5. 5.
    R. Rosenblatt, A. Anderson, Neurocomputing: Foundations of Research, MIT Press (1988) . The most extensive reference book of most of the major papers in that field.Google Scholar
  6. 6.
    E.R. Kandel, J.H. Schwartz, Principles of Neural Science, Elsevier (1985). A well-written overview over the structure and field of neural networks.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden 1998

Authors and Affiliations

  • Cornelia Denz
    • 1
  1. 1.Institut für Angewandte Optik, AG Photorefraktive OptikTechnische Universität DarmstadtDarmstadtGermany

Personalised recommendations