At the Edge of Chaos: Real-Time Computations and Self-Organized Criticality in Recurrent Neural Networks
Abstract
In this paper we analyze the relationship between the computational ca- pabilities of randomly connected networks of threshold gates in the time- series domain and their dynamical properties. In particular we propose a complexity measure which we find to assume its highest values near the edge of chaos, i.e. the transition from ordered to chaotic dynamics. Furthermore we show that the proposed complexity measure predicts the computational capabilities very well: only near the edge of chaos are such networks able to perform complex computations on time series. Ad- ditionally a simple synaptic scaling rule for self-organized criticality is presented and analyzed.
Cite
Text
Bertschinger et al. "At the Edge of Chaos: Real-Time Computations and Self-Organized Criticality in Recurrent Neural Networks." Neural Information Processing Systems, 2004.Markdown
[Bertschinger et al. "At the Edge of Chaos: Real-Time Computations and Self-Organized Criticality in Recurrent Neural Networks." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/bertschinger2004neurips-edge/)BibTeX
@inproceedings{bertschinger2004neurips-edge,
title = {{At the Edge of Chaos: Real-Time Computations and Self-Organized Criticality in Recurrent Neural Networks}},
author = {Bertschinger, Nils and Natschläger, Thomas and Legenstein, Robert A.},
booktitle = {Neural Information Processing Systems},
year = {2004},
pages = {145-152},
url = {https://mlanthology.org/neurips/2004/bertschinger2004neurips-edge/}
}