Learning Algorithms for Artifical Neural Nets for Analog Circuit Implementation

Fathi M. A. Salam
Additional contact information
Fathi M. A. Salam: Michigan State University, Systems and Circuits & Artificial Neural Nets Laboratories Department of Electrical Engineering

A chapter in Computing Science and Statistics, 1992, pp 169-178 from Springer

Abstract: Abstract We describe (supervised and unsupervised) learning rules for continuous-time Artificial Neural Nets (ANNs). For feedforward ANNs, supervised learning is achieved efficiently by modifications to the well-known Error Back-Propagation learning rule. For Feedback ANNs novel learning rules are introduced for supervised learning. The essential feature of all the learning rules is that they lend themselves to analog (all-MOS) circuit realization, and thus they are suitable for implementation using standard (analog) silicon CMOS technology. Circuit implementation of sample learning rules are demonstrated. Results from computer simulations, SPICE simulations, as well as laboratory experiements of circuits and chips substantiate the effectiveness of these rules.

Keywords: Synaptic Weight; Module Chip; Feedback Neural Network; Feedforward ANNs; Steady State Weight (search for similar items in EconPapers)
Date: 1992
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-1-4612-2856-1_22

Ordering information: This item can be ordered from
http://www.springer.com/9781461228561

DOI: 10.1007/978-1-4612-2856-1_22

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().