Synchronization can control regularization in neural systems via correlated noise processes
Name
4527-synchronization-can-control-regularization-in-neural-systems-via-correlated-noise-processes.pdf
Size
345.96 KB
Format
Adobe PDF
Checksum (MD5)
88ae1354d0820a49136a163bd0c98007
Author(s)
Bouvrie, Jacob Vincent
Slotine, Jean-Jacques E
Date Issued
December 2012
Journal
Advances in Neural Information Processing Systems 25 (NIPS 2012)
Publisher
Neural Information Processing Systems Foundation, Inc
Citation
Bouvrie, Jake and Jean-Jacques Slotine. "Synchronization can Control Regularization in Neural Systems via Correlated Noise Processes." Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, Nevada, USA, Neural Information Processing Systems Foundation, December 2012.
Version
Final published version
Abstract
To learn reliable rules that can generalize to novel situations, the brain must be capable of imposing some form of regularization. Here we suggest, through theoretical and computational arguments, that the combination of noise with synchronization provides a plausible mechanism for regularization in the nervous system. The functional role of regularization is considered in a general context in which coupled computational systems receive inputs corrupted by correlated noise. Noise on the inputs is shown to impose regularization, and when synchronization upstream induces time-varying correlations across noise variables, the degree of regularization can be calibrated over time. The resulting qualitative behavior matches experimental data from visual cortex.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/4527-synchronization-can-control-regularization-in-neural-systems-via-correlated-noise-processes
