Continuous restricted Boltzmann machine with an implementable training algorithm

IEE Proceedings: Vision, Image and Signal Processing

Volumn 150, Issue 3, 2003, Pages 153-159

  Chen, H ^a   Murray, A F ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; COMPUTATIONAL METHODS; LEARNING ALGORITHMS; MATHEMATICAL MODELS; RANDOM PROCESSES;

BOLTZMANN MACHINE; GIBBS SAMPLING;

LEARNING SYSTEMS;

EID: 0037768682     PISSN: 1350245X     EISSN: None     Source Type: Journal    
DOI: 10.1049/ip-vis:20030362     Document Type: Article

References (18)

1. Hinton, G.E.: 'Products of experts'. Proceedings of 9th Int. Conf. on Artificial neural networks, (ICANN'99), Edinburgh, Scotland, UK, Sept. 1999, pp. 1-6
2. Hinton, G.E.: 'Training products of experts by minimizing contrastive divergence'. Technical Report 2000, Gatsby Comp. Neuroscience Unit
3. Smolensky, P.: 'Information processing in dynamical systems: foundations of harmony theory' in 'Parallel distributed processing: explorations in the microstructure of cognition' (MIT Press, Cambridge, MA, USA, 1986), Vol. 1, pp. 195-281
4. Murray, A.F.: 'Novelty detection using products of simple experts - a potential architecture for embedded systems', Neural Netw., 2001, 14, pp. 1257-1264
5. Teh, Y.W., and Hinton, G.E.: 'Rate-coded restricted Boltzmann machine for face recognition' in 'Advances in neural information processing system' (MIT Press, Cambridge, MA, USA, 2001), Vol. 13
6. Movellan, J.R.: 'A learning theorem for networks at detailed stochastic equilibrium', Neural Comput., 1998, 10, pp. 1157-1178
7. Chen, H., and Murray, A.F.: 'A continuous restricted Boltzmann machine with hardware-amenable learning algorithm'. Proceedings of 12th Int. Conf. on Artificial neural networks (ICANN2002), Madrid, Spain, Aug. 2002, pp. 358-363
8. Hinton, G.E., and Sejnowski, T.J.: 'Learning and re-learning in Boltzmann machines' in 'Parallel distributed processing: explorations in the microstructure of cognition' (MIR Press, Cambridge, MA, USA, 1986), Vol. 1, pp. 283-317
9. Woodburn, R.J., Astaras, A.A., Dalzell, R.W., Murray, A.F., and McNeill, D.K.: 'Computing with uncertainty in probabilistic neural networks on silicon'. Proceedings 2nd Int. ICSC Symp. on Neural computation, 1999, pp. 470-476
10. Frey, B.J.: 'Continuous sigmoidal belief networks trained using slice sampling' in 'Advances in neural information processing systems' (MIT Press, Cambridge, MA, USA, 1997), Vol. 9, pp. 452-458
11. Movellan, J.R., Mineiro, P., and Williams, R.J.: 'A Monte-Carlo EM approach for partially observable diffusion process: theory and applications to neural networks', Neural Comput., 2002, 14, pp. 1501-1544
12. Marks, T.K., and Movellan, J.R.: 'Diffusion networks, products of experts, and factor analysis'. Technical Report 2001,02., UCSD MPLab. 2001
13. Hopfield, J.J., 'Neurons with graded response have collective computational properties like those of two-state neurons', Proc. Natl. Acad. Sci. USA, 1984, 81, pp. 3088-3092
14. Fleury, P., Woodburn, R.J. and Murray, A.F.: 'Matching analogue hardware with applications using the products of experts algorithm'. Proceedings of IEEE European Symp. on Artificial neural networks, 2001, pp. 63-64
15. Fleury, P., Murray, A.F., and Reekie, M.: 'High-accuracy mixed-signal VLSI for weight modification in contrastive divergence learning'. Proceedings of 12th Int. Conf. on Artificial neural networks (ICANN2002), Madrid, Spain, August 2002, pp. 426-431
16. Alspector, J., Gannett, J.W., Haber, S., Parker, M.B., and Chu, R.: 'A VLSI-efficient technique for generating multiple uncorrelated noise sources and its application to stochastic neural networks', IEEE Trans. Circuits Syst., 1991, 38, pp. 109-123
17. Tarassenko, L., and Clifford, G.: 'Detection of ectopic beats in the electrocardiogram using an autoassociative neural network', Neural Process. Lett., 2001, 14, pp. 15-25
18. Wang, Y., Zhu, Y.S., Thakor, N.V., and Xu, Y.H.: 'A short-time multifractal approach for arrhythmia detection based on fuzzy neural network', IEEE Trans. Biomed. Eng., Sept. 2001, 48, pp. 989-995