Abstract
Recent encouraging results have occurred in the application of neuromorphic, ie. neural network inspired, software simulations of speech synthesis, word recognition, and image processing. Hardware implementations of neuromorphic systems are required for real-time applications such as control and signal processing. Two disparate groups of workers are interested in VLSI hardware implementations of neural networks. The first is interested in electronic-based implementations of neural networks and use standard or custom VLSI chips for the design. The second group wants to build fault tolerant adaptive VLSI chips and are much less concerned with whether the design rigorously duplicates the neural models. In either case, the central issue in construction of a electronic neural network is that the design constraints of VLSI differ from those of biology (Walker and Akers 1988). In particular, the high fan-in/fan-outs of biology impose connectivity requirements such that the electronic implementation of a highly interconnected biological neural networks of just a few thousand neurons would require a level of connectivity which exceeds the current or even projected interconnection density of ULSI systems. Fortunately, highly-layered limited interconnected networks can be formed that are functionally equivalent to highly connected systems (Akers et al. 1988). Highly layered, limited-interconnected architectures are especially well suited for VLSI implementations. The objective of our work is to design highly layered, limited-interconnect synthetic neural architectures and develop training algorithms for systems made from these chips. These networks are specifically designed to scale to tens of thousands of processing elements on current production size dies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abu-Mostafa, Y.S., and Psaltis, D., “Optical Neural Computers,” Scientific American, vol. 256, no. 3, March, 1987.
Akers, L.A., Walker, M.R., Ferry, D.K., and Grondin, R.O., “Limited Interconnectivity in Synthetic Neural Systems”, in Rolf Eckmiller and Christopher v.d. Malsburg eds., Neural Computers. Springer-Verlag, 1988.
Baum, E.B. “On the Capabilities of Multilayer Perceptrons”, IEEE Conference on Neural Information Processing Systems — Natural and Synthetic, Denver Colo., November, 1987.
Ferry, D.K., Akers, L.A., and Greeneich, E., Ultra Large Scale Integrated Microelectronics. Prentice-Hall, 1988.
Hecht-Nielsen, R., “Kolmogorov’s Mapping Neural Network Existance Theorem,” Proceedings of the IEEE First International Conference on Neural Networks, vol. 3, pp. 11–12, 1987.
Lippman, R.P., “An Introduction to Computing with Neural Nets,” IEEE ASSP Magazine, pl4–22, April, 1987.
McClelland, J.L., “Resource Requirements of Standard and Programmable Nets,” in D.E. Rummelhard and J.L. McClelland eds., Paralell Distributed Processing — Volume 1: Foundations. MIT Press, 1986
Myers, G.J., Yu, A.Y. and House, D.L., “Microprocessor Technology Trends,” Proceedings of the IEEE, Vol. 74, No. 12, p. 1605, Dec. 1986.
Plaut, D.C., Nowlan, S.J., and Hinton, G.E., “Experiments on Learning by Back Propagation,” Carnegie-Mellon University, Dept. of Computer Science Technical Report, June, 1986
Walker, M.R., and Akers, L.A., “A Neuromorphic Approach to Adaptive Digital Circuitry,” Proceedings of the Seventh Annual International IEEE Phoenix Conference on Computers and Communications, p. 19, March 16, 1988.
Widrow, B., and Stearns, S.D., Adaptive Signal Processing. Prentice-Hall, 1985.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1989 Kluwer Academic Publishers
About this chapter
Cite this chapter
Akers, L., Walker, M., Ferry, D., Grondin, R. (1989). A Limited-Interconnect, Highly Layered Synthetic Neural Architecture. In: Delgado-Frias, J.G., Moore, W.R. (eds) VLSI for Artificial Intelligence. The Kluwer International Series in Engineering and Computer Science, vol 68. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1619-0_20
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1619-0_20
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8895-4
Online ISBN: 978-1-4613-1619-0
eBook Packages: Springer Book Archive