Abstract
Recurrent networks are trained to memorize their input better, often in the hopes that such training will increase the ability of the network to predict. We show that networks designed to memorize input can be arbitrarily bad at prediction. We also find, for several types of inputs, that one-node networks optimized for prediction are nearly at upper bounds on predictive capacity given by Wiener filters and are roughly equivalent in performance to randomly generated five-node networks. Our results suggest that maximizing memory capacity leads to very different networks than maximizing predictive capacity and that optimizing recurrent weights can decrease reservoir size by half an order of magnitude.
- Received 29 June 2017
- Revised 14 August 2017
- Corrected 22 October 2018
DOI:https://doi.org/10.1103/PhysRevE.96.032308
©2017 American Physical Society
Physics Subject Headings (PhySH)
Corrections
22 October 2018