Skip to main content

A low-cost application-specific neural network implementation with floating gate wàghts

Publication ,  Conference
Thomsen, A; Brooke, MA
Published in: Proceedings of the International Joint Conference on Neural Networks
January 1, 1992

This paper presents the technology and design philosophy for low-cost appUcation-specific neural netwoik implementations through MOSIS. The advantage of applying a low-cost custom-made special purpose networic for a given problem over the application of available general purpose networics is discussed. The special purpose netwodcs use floating gate devices for weight storage. The presented design approach allows the designer to implement any knowledge about the problem to be solved into hardware, thus reducing circuit complexity and training time. The example of a simple network for linear and non-linear voltage-to-current conversion illustrates the technique.

Duke Scholars

Published In

Proceedings of the International Joint Conference on Neural Networks

DOI

Publication Date

January 1, 1992

Volume

2

Start / End Page

565 / 570
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Thomsen, A., & Brooke, M. A. (1992). A low-cost application-specific neural network implementation with floating gate wàghts. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 565–570). https://doi.org/10.1109/IJCNN.1992.226928
Thomsen, A., and M. A. Brooke. “A low-cost application-specific neural network implementation with floating gate wàghts.” In Proceedings of the International Joint Conference on Neural Networks, 2:565–70, 1992. https://doi.org/10.1109/IJCNN.1992.226928.
Thomsen A, Brooke MA. A low-cost application-specific neural network implementation with floating gate wàghts. In: Proceedings of the International Joint Conference on Neural Networks. 1992. p. 565–70.
Thomsen, A., and M. A. Brooke. “A low-cost application-specific neural network implementation with floating gate wàghts.” Proceedings of the International Joint Conference on Neural Networks, vol. 2, 1992, pp. 565–70. Scopus, doi:10.1109/IJCNN.1992.226928.
Thomsen A, Brooke MA. A low-cost application-specific neural network implementation with floating gate wàghts. Proceedings of the International Joint Conference on Neural Networks. 1992. p. 565–570.

Published In

Proceedings of the International Joint Conference on Neural Networks

DOI

Publication Date

January 1, 1992

Volume

2

Start / End Page

565 / 570