Implementation-Oriented Theory for Cellular Neural Networks

  • Peter Kinget
  • Michiel Steyaert
Chapter
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 384)

Abstract

To design analog VLSI circuits that implement the parallel processing systems developed by system theory researchers, the gap between the world of system theory and the world of analog circuit design has to be bridged. Both worlds use different conventions, use different resources, have different optimization goals and different constraints. In table 3.1 some of these differences are summarized. The theoretical descriptions of systems use a much higher level of abstraction than the circuit implementations. Translating the abstract description of a system as an algorithm or a block diagram using ideal primitive computing blocks, into an electronic function with the same behavior, requires a lot of extra information. The circuit designer is especially confronted with the limitations of the circuit blocks. A circuit implementation has extra unwanted poles in the transfer function compared to the system-level description; these poles can cause unexpected instabilities which make the circuit useless. The non-linear characteristics of electronic devices cause non-linear behavior of the blocks and limit the signal ranges that can be processed.

Keywords

Correct Operation Cellular Neural Network Circuit Implementation Accuracy Specification Dynamic Route 
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.

Copyright information

© Springer Science+Business Media Dordrecht 1997

Authors and Affiliations

  • Peter Kinget
    • 1
  • Michiel Steyaert
    • 1
  1. 1.Katholieke Universiteit LeuvenHeverleeBelgium

Personalised recommendations