ML Anthology

A Local Algorithm to Learn Trajectories with Stochastic Neural Networks

Javier R. Movellan
NeurIPS 1993 pp. 83-87
/neurips/1993/movellan1993neurips-local/

Abstract

This paper presents a simple algorithm to learn trajectories with a continuous time, continuous activation version of the Boltzmann machine. The algorithm takes advantage of intrinsic Brownian noise in the network to easily compute gradients using entirely local computations. The algorithm may be ideal for parallel hardware implementations.

PDF NeurIPS Semantic Scholar

Cite

Text

Movellan. "A Local Algorithm to Learn Trajectories with Stochastic Neural Networks." Neural Information Processing Systems, 1993.

Markdown

[Movellan. "A Local Algorithm to Learn Trajectories with Stochastic Neural Networks." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/movellan1993neurips-local/)

BibTeX

@inproceedings{movellan1993neurips-local,
  title     = {{A Local Algorithm to Learn Trajectories with Stochastic Neural Networks}},
  author    = {Movellan, Javier R.},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {83-87},
  url       = {https://mlanthology.org/neurips/1993/movellan1993neurips-local/}
}