Minimising Contrastive Divergence in Noisy, Mixed-Mode VLSI Neurons
Abstract
This paper presents VLSI circuits with continuous-valued proba- bilistic behaviour realized by injecting noise into each computing unit(neuron). Interconnecting the noisy neurons forms a Contin- uous Restricted Boltzmann Machine (CRBM), which has shown promising performance in modelling and classifying noisy biomed- ical data. The Minimising-Contrastive-Divergence learning algo- rithm for CRBM is also implemented in mixed-mode VLSI, to adapt the noisy neurons’ parameters on-chip.
Cite
Text
Chen et al. "Minimising Contrastive Divergence in Noisy, Mixed-Mode VLSI Neurons." Neural Information Processing Systems, 2003.Markdown
[Chen et al. "Minimising Contrastive Divergence in Noisy, Mixed-Mode VLSI Neurons." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/chen2003neurips-minimising/)BibTeX
@inproceedings{chen2003neurips-minimising,
title = {{Minimising Contrastive Divergence in Noisy, Mixed-Mode VLSI Neurons}},
author = {Chen, Hsin and Fleury, Patrice and Murray, Alan F.},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {1011-1018},
url = {https://mlanthology.org/neurips/2003/chen2003neurips-minimising/}
}