论文信息 - Pulse-stream circuits for on-chip learning in analogue VLSI neural networks

Pulse-stream circuits for on-chip learning in analogue VLSI neural networks

We explain the advantages of the Virtual-Targets algorithm for learning in a VLSI Multilayer Perceptron, outline the design issues, and describe fabricated circuits that implement the main algorithmic functions. The test-chip described is a precursor to a larger device incorporating full on-chip learning.<<ETX>>

Alan F. Murray | Robin Woodburn | H. Martin Reekie

[1] David Blair Kirk. Accurate and Precise Computation using Analog VLSI, with Applications to Computer Graphics and Neural Networks , 1993 .

[2] Alan F. Murray. Analogue noise-enhanced learning in neural network circuits , 1991 .

[3] Daniele D. Caviglia,et al. An experimental analog VLSI neural network with on-chip back-propagation learning , 1992, ESSCIRC '92: Eighteenth European Solid-State Circuits conference.

[4] Alan F. Murray. Analog VLSI and multi-layer perceptrons - Accuracy, noise and on-chip learning , 1992, Neurocomputing.

[5] Lionel Tarassenko,et al. On-Chip Learning With Analogue Vlsi Neural Networks , 1993, Int. J. Neural Syst..

[6] G. Bogason. Generation of a neuron transfer function and its derivatives , 1993 .

[7] Alan F. Murray,et al. Generic Analog Neural Computation - The Epsilon Chip , 1992, NIPS.

[8] Marwan A. Jabri,et al. Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks , 1992, IEEE Trans. Neural Networks.