Format

Send to

Choose Destination
Front Comput Neurosci. 2009 Oct 30;3:23. doi: 10.3389/neuro.10.023.2009. eCollection 2009.

SORN: a self-organizing recurrent neural network.

Author information

1
Frankfurt Institute of Advanced Studies, Johann Wolfgang Goethe University Frankfurt am Main, Germany. lazar@fias.uni-frankfurt.de

Abstract

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:

intrinsic plasticity; recurrent neural networks; reservoir computing; synaptic plasticity; time series prediction

Supplemental Content

Full text links

Icon for Frontiers Media SA Icon for PubMed Central
Loading ...
Support Center