Pulse-based circuits and methods for probabilistic neural computation

Proceedings of the 7th International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems, MicroNeuro 1999

Volumn , Issue , 1999, Pages 96-102

  Astaras, A ^a   Dalzell, R ^a   Murray, A ^a   Reekie, M ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

FUZZY INFERENCE; FUZZY LOGIC; INTEGRATED CIRCUIT DESIGN; LOCKS (FASTENERS); MICROELECTRONICS; SIGNAL PROCESSING; STOCHASTIC MODELS; STOCHASTIC SYSTEMS; TIMING CIRCUITS; VOLTAGE CONTROL;

CURRENT INPUT; DESIGN AND SIMULATION; HARDWARE IMPLEMENTATIONS; HARDWARE MODELS; HARDWARE PROTOTYPE; NEURAL ARCHITECTURES; NEURAL COMPUTATIONS; SQUASHING FUNCTIONS;

HARDWARE;

EID: 84871607175     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/MN.1999.758851     Document Type: Conference Paper

References (29)

1. J. Alspector, J. Gannett, S. Haber, M. Parker, and R. Chu. Generating multiple analog noise sources from a single linear feedback shift register with neural network applications. In Proceedings-IEEE International Symposium on Circuits and Systems, volume 2. IEEE Service Center, 1990
2. 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 Transactions on Circuits and Systems, 38(1):109-123, Jan. 1991
3. A. Astaras. CMOS VLSI design and testing for the Helmholtz Machine artificial neural network architecture. Technical report, Department of Electronics and Electrical Engineering, The University of Edinburgh, King's Buildings, Mayfield Road, EH9 3JL, Scotland, UK, April 1998
4. P. Dayan, P. E. Hinton, R. M. Neal, and R. Zemel. The Helmholtz Machine. Neural Computation, 7(5):889-904, September 1995
5. A. Dempster, N. Laird, and D. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B, 39:1-38, 1977
6. P. Edwards and A. Murray. Fault-tolerance via weight-noise in analog VLSI implementations-A case study with EPSILON. IEEE Proceedingson Circuits and Systems II : Analog and Digital Signal Processing, 45(9):1255-1262, 1998
7. B. J. Frey, P. Dayan, and G. E. Hinto. Computational and Psychophysical Mechanisms of Visual Coding, chapter A simple algorithm that discovers efficient perceptual codes. Cambridge University Press, New York, NY, USA, 1997
8. G. Gorry. Computer-assisted clinical decision making. Methods of Information in Medicine, 12:45-51, 1973
9. A. Hamilton. Synaptic weight representation in pulsed neural network VLSI : Voltage or current? Proc. International Conference on Neural Information Processing, Seoul, pages 353-358, October 1994
10. A. Hamilton, S. Churcher, P. Edwards, G. Jackson,A. Murray, and H. Reekie. Pulse stream VLSI circuits and systems : The EPSILON neural network chipset. International Journal of Neural Systems, 4(4):395-406, 1993
11. G. E. Hinton, P. Dayan, B. J. Frey, and R. M. Neal. The wake-sleep algorithm for unsupervised neural networks. Science, 268(5214):1158-1161,May 1995
12. G. E. Hinton and Z. Ghahramani. Generative models for discovering sparse distributed representations. Philosophical Transactions of the Royal Society of London: Series B, 352:1177-1190,August 1997
13. G. E. Hinton and T. J. Sejnowski. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, volume 1, chapter Learning and relearning in Boltzmann machines. MIT Press, Cambridge, MA, USA, 1986
14. T. Jaakkola, L. K. Saul, and M. I. Jordan. Fast learning by bounding likelihoods in sigmoid type belief networks, chapter Advances in Neural Information Processing Systems. MIT Press, Cambridge,MA, USA, 1986
15. G. Jackson, A. Hamilton, and A. Murray. The EPSILON processor card: A framework for analog neural computation. In Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Sytems., pages 280-286. IEEE Computer Society Press, 1994
16. D. Mayes, A. Hamilton, A. Murray, and H. Reekie. Pulsed VLSI radial basis function chip. In Proceedings-IEEE International Symposium on Circuits and Systems, volume 3, pages 297-300. IEEE, Piscataway, NJ, USA, May 1996
17. D. Mayes, J. Louvet, and A. Hamilton. Dymples-an analogue current mode pulsed synapse. In Proceedings of the 4th International Conference on Artificial Neural Networks, pages 477-482. IEE, Stevenage, England, UK, Jun 1995
18. A. F. Murray. Pulse arithmetic in VLSI neural networks. IEEE Micro, 9(6):64-74, 1989
19. A. F. Murray, D. Baxter, Z. Butler, S. Churcher, A. Hamilton, H. M. Reekie, and L. Tarassenko. Innovations in pulse-stream neural VLSI. In IEEE Workshop on Microelectronics for Neural Networks, pages 8-15, Dortmund, 1990
20. A. F. Murray, S. Churcher, A. Hamilton, A. J. Homes, G. B. Jackson, H. M. Reekie, and R. J. Woodburn. Pulse stream VLSI neural networks. IEEE Micro, 14(3):29-39, June 1994
21. R. M. Neal. Connectionist learning of belief networks. Artificial Intelligence, 56:71-113, 1992
22. C. Park, K. Buckmann, J. Diamond, U. Santoni, TheS.C., M. Holler, M. Glier, C. Scofield, and L. Nunez. Radial basis function neural network with on-chip learning. In Proceedings of the International Joint Conference on Neural Network, volume 3, pages 3035-3038. IEEE, Piscataway, NJ, USA, 1993
23. J. Pearl. Fusion, propagation and structuring in Belief Networks. Artificial Intelligence, 19(3):241-288, 1986
24. J. Quero, J. Ortega, C. Janer, and L. Franquelo. VLSI implementation of a fully parallel stochastic neural network. In International Conference on Neural Networks. IEEE World Congress on Computational Intelligence, pages 2040-5. IEEE, 1994
25. M. van Daalen, T. Kosel, P. Jeavons, and J. Shawe-Taylor. Emergent activation functions from a stochastic bit-stream neuron. Electronics Letters, 30(4):331-333, February 1994
26. M. vanDaalen, P. Jeavons, J. ShaweTaylor, and D. Cohen. Device for generating binary sequences for stochastic computing. Electronics Letters, 29(1):80-81, January 1993
27. J. Zhao and J. Shawe-Taylor. Stochastic connection neural networks. In Proceedings of the 4th International Conference on Artificial Neural Networks, pages 35-39, Cambridge, England, UK, Jun 1995. IEE
28. J. Zhao and J. Shawe-Taylor. Recurrent network with stochastic weights. In IEEE International Conference on Neural Networks, volume 2, pages 1302-1307, Piscataway, NJ, USA, 1996. IEEE
29. J. Zhao, J. Shawe-Taylor, and M. van Daalen. Learning in stochastic bit stream neural networks. Neural Networks, 9(6):991-998, August 1996