A formulation for the design of neural processors
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 173-180 vol.1
- https://doi.org/10.1109/icnn.1988.23845
Abstract
The author presents a mathematical framework for the design of neural networks as associative memories or as pattern classifiers. This framework takes into account the characteristics and the limitations of the electrical components which are the building blocks for the proposed devices. He also presents conditions that given vectors must satisfy to successfully store them in the network. The conditions suggest a preprocessing procedure of the desired memories to render them storable.Keywords
This publication has 3 references indexed in Scilit:
- On the analysis and design of neural nets with an implementation via CMOS VLSIPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural NetworksPublished by Elsevier ,1987
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984