Authors:
Part of the book series: The Springer International Series in Engineering and Computer Science (SECS, volume 314)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (14 chapters)
-
Front Matter
-
Back Matter
About this book
Starting with the derivation of a specification and ending with its hardware implementation, analog hard-wired, feed-forward neural networks with on-chip back-propagation learning are designed in their entirety. On-chip learning is necessary in circumstances where fixed weight configurations cannot be used. It is also useful for the elimination of most mis-matches and parameter tolerances that occur in hard-wired neural network chips.
Fully analog neural networks have several advantages over other implementations: low chip area, low power consumption, and high speed operation.
Feed-Forward Neural Networks is an excellent source of reference and may be used as a text for advanced courses.
Authors and Affiliations
-
MESA Research Institute, University of Twente, Netherlands
Anne-Johan Annema
Bibliographic Information
Book Title: Feed-Forward Neural Networks
Book Subtitle: Vector Decomposition Analysis, Modelling and Analog Implementation
Authors: Anne-Johan Annema
Series Title: The Springer International Series in Engineering and Computer Science
DOI: https://doi.org/10.1007/978-1-4615-2337-6
Publisher: Springer New York, NY
-
eBook Packages: Springer Book Archive
Copyright Information: Springer Science+Business Media New York 1995
Hardcover ISBN: 978-0-7923-9567-6Published: 31 May 1995
Softcover ISBN: 978-1-4613-5990-6Published: 13 July 2013
eBook ISBN: 978-1-4615-2337-6Published: 06 December 2012
Series ISSN: 0893-3405
Edition Number: 1
Number of Pages: XIII, 238
Topics: Circuits and Systems, Electrical Engineering, Complex Systems, Statistical Physics and Dynamical Systems