Share Email Print

Proceedings Paper

High-resolution synaptic weights and hardware-in-the-loop learning
Author(s): Taher Daud; Tuan A. Duong; Mua D. Tran; Harry Langenbacher; Anilkumar P. Thakoor
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Artificial neural network paradigms are derived from biological nervous system and are characterized by massive parallelism. These networks have shown the capabilities of processing input-output mapping operations even where the transformation rules are not known, partially known, or ill-defined. For high-speed processing, we have fabricated neural network architectures as building-block chips with either a 32 X 32 matrix of synapses or a 32 X 31 array of synapses along with 32 neurons along a diagonal for a 32 X 32 matrix. Reconfigurability allows a variety of architectures from fully recurrent to fully feedforward, including constructive architectures such as cascade correlation. Further, a variety of gradient-descent learning algorithms have been implemented. Additionally, the chips being cascadable, larger size networks are easily assembled. An innovative scheme of combining two identical synapses on two respective chips in parallel nominally doubles the bit resolution from 7 bits (6-bit + sign) to 13 bits (12-bit + sign). We describe the feedforward net obtained by assembly of 8 chips on a board with nominally 13 bits of resolution for a hardware-in-the-loop learning of a feature classification problem involving map-data. This neural net hardware with 27 analog inputs and 7 outputs is able to learn to classify the features and provide the required output map at high speed with 89% accuracy. This result, with hardware's lower precision, etc., compares favorably with an accuracy of 92% obtained both by a neural network software simulation (floating point accuracy of synaptic weights) and a statistical technique of k-nearest neighbors.

Paper Details

Date Published: 28 March 1995
PDF: 12 pages
Proc. SPIE 2424, Nonlinear Image Processing VI, (28 March 1995); doi: 10.1117/12.205250
Show Author Affiliations
Taher Daud, Jet Propulsion Lab. (United States)
Tuan A. Duong, Jet Propulsion Lab. (United States)
Mua D. Tran, Jet Propulsion Lab. (United States)
Harry Langenbacher, Jet Propulsion Lab. (United States)
Anilkumar P. Thakoor, Jet Propulsion Lab. (United States)

Published in SPIE Proceedings Vol. 2424:
Nonlinear Image Processing VI
Edward R. Dougherty; Jaakko T. Astola; Harold G. Longbotham; Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?