论文信息 - Matching analogue hardware with applications using the Products of Experts algorithm

Matching analogue hardware with applications using the Products of Experts algorithm

Probabilistic algorithms o er a means of computing that works with the grain of analogue hardware, rather than against it. This paper proposes the use of such an algorithm in applications where the advantages of analogue hardware are most likely to be realised.

[1] Radford M. Neal. Connectionist Learning of Belief Networks , 1992, Artif. Intell..

[2] Geoffrey E. Hinton,et al. SMEM Algorithm for Mixture Models , 1998, Neural Computation.

[3] A. Murray,et al. Computing with Uncertainty in Probabilistic Neural Networks on Silicon , 2000 .

[4] Judea Pearl,et al. Fusion, Propagation, and Structuring in Belief Networks , 1986, Artif. Intell..

[5] G. Kane. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[6] Geoffrey E. Hinton. Training Products of Experts by Maximizing Contrastive Likelihood , 1999 .

[7] Alan F. Murray,et al. Implementing Artificial Neural Networks in Analogue VLSI , 1997, ICONIP.

[8] Alan F. Murray,et al. Pulse-based circuits and methods for probabilistic neural computation , 1999, Proceedings of the Seventh International Conference on Microelectronics for Neural, Fuzzy and Bio-Inspired Systems.

[9] Torsten Lehmann,et al. On-chip learning in pulsed silicon neural networks , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[10] M. V. Rossum,et al. In Neural Computation , 2022 .

[11] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .