A unifying algorithm/architecture for artificial neural networks
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 2505-2508
- https://doi.org/10.1109/icassp.1989.266976
Abstract
A generic iterative model is presented for a wide variety of artificial neural networks (ANNs): single-layer feedback networks, multilayer feed-forward networks, hierarchical competitive networks, and hidden Markov models. Unifying mathematical formulations are provided for both the retrieving and learning phases of ANNs. Based on the unifying mathematical formulation, a programmable universal ring systolic array is derived for both phases. It maximizes the strength of VLSI in terms of intensive and pipelined computing and yet circumvents the limitation on communication. Hardware implementation for the processing units based on CORDIC techniques is discussed.<>Keywords
This publication has 10 references indexed in Scilit:
- Self-organization in a perceptual networkComputer, 1988
- Neural nets for adaptive filtering and adaptive pattern recognitionComputer, 1988
- Parallel architectures for artificial neural netsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- An introduction to hidden Markov modelsIEEE ASSP Magazine, 1986
- Distributed memory and the representation of general and specific information.Journal of Experimental Psychology: General, 1985
- A Learning Algorithm for Boltzmann Machines*Cognitive Science, 1985
- Feature Discovery by Competitive Learning*Cognitive Science, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectorsBiological Cybernetics, 1976