nips nips2003 nips2003-129 nips2003-129-reference knowledge-graph by maker-knowledge-mining

129 nips-2003-Minimising Contrastive Divergence in Noisy, Mixed-mode VLSI Neurons


Source: pdf

Author: Hsin Chen, Patrice Fleury, Alan F. Murray

Abstract: This paper presents VLSI circuits with continuous-valued probabilistic behaviour realized by injecting noise into each computing unit(neuron). Interconnecting the noisy neurons forms a Continuous Restricted Boltzmann Machine (CRBM), which has shown promising performance in modelling and classifying noisy biomedical data. The Minimising-Contrastive-Divergence learning algorithm for CRBM is also implemented in mixed-mode VLSI, to adapt the noisy neurons’ parameters on-chip. 1


reference text

[1] H. Chen and A. Murray, “A continuous restricted boltzmann machine with an implementable training algorithm,” IEE Proc. of Vision, Image and Signal Processing, vol. 150, no. 3, pp. 153–158, 2003.

[2] T. Tang, H. Chen, and A. Murray, “Adaptive Stochastic Classifier for Noisy pH-ISFET Measurements,” in Proceedings of Thirteenth International Conference on Artificial Neural Networks (ICANN2003), (Istanbul, Turkey), pp. 638–645, Jun. 2003.

[3] G. E. Hinton, “Training products of experts by minimizing contrastive divergence,” Neural Computation, vol. 14, no. 8, pp. 1771–1800, 2002.

[4] B. J. Frey, “Continuous sigmoidal belief networks trained using slice sampling,” Advances in Neural Information Processing Systems, vol. 9, pp. 452–458, 1997.

[5] A. F. Murray, “Novelty detection using products of simple experts-a potential architecture for embedded systems,” Neural Networks, vol. 14, no. 9, pp. 1257–1264, 2001.

[6] H. Chible, “Analog circuit for synapse neural networks vlsi implementation,” The 7th IEEE Int. Conf. on Electronics, Circuits and Systems (ICECS 2000), vol. 2, pp. 1004–1007, 2000.

[7] M. Banu and Y. Tsividis, “Floating voltage-controlled resistors in cmos technology,” Electronics Letters, vol. 18, pp. 678–679, 1982.

[8] E. Vittoz, “Mos transistors operated in the lateral bipolar mode and their application in cmos technology,” IEEE Journal of Solid-State Circuits, vol. sc-18, no. 3, pp. 273–279, 1983.

[9] J. Alspector, J. W. Gannett, S. Haber, M. B. Parker, and R. Chu, “A vlsi-efficient technique for generating multiple uncorrelated noise sources and its application to stochastic neural networks,” IEEE Trans. Circuits and Systems, vol. 38, no. 1, pp. 109–123, 1991.

[10] P. Fleury and A. Murray, “Mixed-signal vlsi implementation of the product of experts’ minimizing contrastive divergence learning scheme,” in IEEE Proc. of the Int. Sym. on Circuits and Systems (ISCAS 2003), vol. 5, (Bangkok, Thailand), pp. 653–656, May 2003.

[11] G. Wegmann and E. Vittoz, “Basic principles of accurate dynamic current mirrors,” IEE Proc. on Circuits, Devices and Systems, vol. 137, pp. 95–100, April 1990.

[12] G. Cauwenberghs, “An analog vlsi recurrent neural network,” IEEE Tran. on Neural Networks, vol. 7, pp. 346–360, Mar. 1996.