Time Dependent Adaptive Neural Networks
Abstract
A comparison of algorithms that minimize error functions to train the trajectories of recurrent networks, reveals how complexity is traded off for causality. These algorithms are also related to time-independent fonnalisms. It is suggested that causal and scalable algorithms are possible when the activation dynamics of adaptive neurons is fast compared to the behavior to be learned. Standard continuous-time recurrent backpropagation is used in an example.
Cite
Text
Pineda. "Time Dependent Adaptive Neural Networks." Neural Information Processing Systems, 1989.Markdown
[Pineda. "Time Dependent Adaptive Neural Networks." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/pineda1989neurips-time/)BibTeX
@inproceedings{pineda1989neurips-time,
title = {{Time Dependent Adaptive Neural Networks}},
author = {Pineda, Fernando J.},
booktitle = {Neural Information Processing Systems},
year = {1989},
pages = {710-718},
url = {https://mlanthology.org/neurips/1989/pineda1989neurips-time/}
}