Spiking Boltzmann Machines
Abstract
We first show how to represent sharp posterior probability distribu(cid:173) tions using real valued coefficients on broadly-tuned basis functions. Then we show how the precise times of spikes can be used to con(cid:173) vey the real-valued coefficients on the basis functions quickly and accurately. Finally we describe a simple simulation in which spik(cid:173) ing neurons learn to model an image sequence by fitting a dynamic generative model.
Cite
Text
Hinton and Brown. "Spiking Boltzmann Machines." Neural Information Processing Systems, 1999.Markdown
[Hinton and Brown. "Spiking Boltzmann Machines." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/hinton1999neurips-spiking/)BibTeX
@inproceedings{hinton1999neurips-spiking,
title = {{Spiking Boltzmann Machines}},
author = {Hinton, Geoffrey E. and Brown, Andrew D.},
booktitle = {Neural Information Processing Systems},
year = {1999},
pages = {122-128},
url = {https://mlanthology.org/neurips/1999/hinton1999neurips-spiking/}
}