论文信息 - A Compact and Fast Silicon Implementation for Layered Neural Nets

A Compact and Fast Silicon Implementation for Layered Neural Nets

In this paper we present an architecture for implementation of artificial layered neural networks. The building blocks of the architecture are simple processing elements properly interconnected to a number of shift registers which provide the processing elements with data and weights. The paper concentrates on optimization of the architecture with respect to the three main parameters of silicon area requirements, computational latency and throughput.

[1] F. Blayo,et al. A reconfigurable WSI neural network , 1989, [1989] Proceedings International Conference on Wafer Scale Integration.

[2] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[3] Nelson Morgan,et al. Applications of neural-network (NN) signal processing in brain research , 1988, IEEE Trans. Acoust. Speech Signal Process..

[4] Philip C. Treleaven,et al. Computer Architectures for Artificial Intelligence , 1986, Future Parallel Computers.

[5] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6] S. Y. Kung,et al. Digital VLSI architectures for neural networks , 1989, IEEE International Symposium on Circuits and Systems,.

[7] L. E. Atlas,et al. A study of regular architectures for digital implementation of neural networks , 1989, IEEE International Symposium on Circuits and Systems,.

[8] S. Y. King. Parallel architectures for artificial neural nets , 1988, [1988] Proceedings. International Conference on Systolic Arrays.

[9] G. Storti Gajani,et al. Alternative Approaches for Mapping Neural Networks onto Silicon , 1989 .

[10] Mariagiovanna Sami,et al. Multistage Interleaved Architectures for Implementation of Neural Networks , 1989 .

[11] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .