论文信息 - Analogue computation using VLSI neural network devices

Analogue computation using VLSI neural network devices

Results are presented demonstrating analogue neural network computation using VLSI pulse-stream devices. Synapse weight storage is dynamic, and the multiply and add functions are performed by a switched capacitor circuit. Used on a mobile robot localisation task, the neural VLSI devices achieve results within 1.2% of those of a SUN workstation.

Alan F. Murray | Lionel Tarassenko | Michael Brownlow

[1] Lawrence D. Jackel,et al. VLSI implementation of a neural network model , 1988, Computer.

[2] Michel Verleysen,et al. Neural networks for high-storage content-addressable memory: VLSI circuit and learning algorithm , 1989 .

[3] Lawrence D. Jackel,et al. VLSI implementation of a neural network memory with several hundreds of neurons , 1987 .

[4] Alan F. Murray,et al. Programmable Analog Pulse-Firing Neural Networks , 1988, NIPS.

[5] Carver A. Mead,et al. VLSI architectures for implementation of neural networks , 1987 .

[6] Alan F. Murray,et al. Fully-Programmable Analogue VLSI Devices for the Implementation of Neural Networks , 1989 .

[7] Alan F. Murray,et al. Asynchronous arithmetic for VLSI neural systems , 1987 .