TY  - JOUR
A1  - Lazar, Andreea
A1  - Pipa, Gordon
A1  - Triesch, Jochen
T1  - SORN : a self-organizing recurrent neural network
T2  - Frontiers in computational neuroscience
N2  - 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
KW  - synaptic plasticity
KW  - intrinsic plasticity
KW  - recurrent neural networks
KW  - reservoir computing
KW  - time series prediction
Y1  - 2010
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/20110
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30-83842
SN  - 1662-5188
N1  - 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.
VL  - 3
IS  - Art. 23
SP  - 1
EP  - 9
PB  - Frontiers Research Foundation
CY  - Lausanne
ER  -