SORN : a self-organizing recurrent neural network

  • Understanding the dynamics of recurrent neural networks is crucial for explaining how the brain processes information. In the neocortex, a range of different plasticity mechanisms are shaping recurrent networks into effective information processing circuits that learn appropriate representations for time-varying sensory stimuli. However, it has been difficult to mimic these abilities in artificial neural network models. Here we introduce SORN, a self-organizing recurrent network. It combines three distinct forms of local plasticity to learn spatio-temporal patterns in its input while maintaining its dynamics in a healthy regime suitable for learning. The SORN learns to encode information in the form of trajectories through its high-dimensional state space reminiscent of recent biological findings on cortical coding. All three forms of plasticity are shown to be essential for the network's success. Keywords: synaptic plasticity, intrinsic plasticity, recurrent neural networks, reservoir computing, time series prediction

Download full text files

Export metadata

Author:Andreea LazarORCiDGND, Gordon PipaORCiDGND, Jochen TrieschORCiD
Pubmed Id:
Parent Title (English):Frontiers in computational neuroscience
Publisher:Frontiers Research Foundation
Place of publication:Lausanne
Contributor(s):Hava T. Siegelmann
Document Type:Article
Date of Publication (online):2010/10/26
Year of first Publication:2009
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2010/10/26
Tag:intrinsic plasticity; recurrent neural networks; reservoir computing; synaptic plasticity; time series prediction
Issue:Art. 23
Page Number:9
First Page:1
Last Page:9
Copyright: © 2009 Lazar, Pipa and Triesch.This is an open-access article subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited.
Source:Frontiers in computational neuroscience 2009, 3:23 ; doi: 10.3389/neuro.10.023.2009
Institutes:Physik / Physik
Wissenschaftliche Zentren und koordinierte Programme / Frankfurt Institute for Advanced Studies (FIAS)
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):License LogoDeutsches Urheberrecht