Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Stochastic gradient ascent learning with spike timing dependent plasticity

Stochastic gradient ascent learning with spike timing dependent plasticity Vieira et al. BMC Neuroscience 2011, 12(Suppl 1):P250 http://www.biomedcentral.com/1471-2202/12/S1/P250 POSTER PRESENTATION Open Access Stochastic gradient ascent learning with spike timing dependent plasticity Joana Vieira , Orlando Arévalo, Klaus Pawelzik From Twentieth Annual Computational Neuroscience Meeting: CNS*2011 Stockholm, Sweden. 23-28 July 2011 Stochastic gradient ascent learning exploits correlations formulation of spike timing dependent plasticity (STDP) of parameter variations with overall success of a system. [3]whenit iscombinedwithareward signal. Here we This algorithmic idea has been related to neuronal net- present conditions under which reward modulated work learning by postulating eligibility traces at STDP is in fact guaranteed to maximize expected synapses, which make them selectable for synaptic reward. We present numerical simulations underlining changes depending on later reward signals ([1] and [2]). the relevance of realistic STDP models for reward Formalizations of the synaptic and neuronal dynamics dependent learning. In particular, we find that the non- supporting gradient ascent learning in terms of differen- linear adaptation to pre- and post-synaptic activities of tial equations exhibit strong similarities with a recent STDP [3] contributes to stable learning. Figure 1 Learning the XOR function with a reward modulated STDP rule. Left: Output activity versus training episode in a feed forward network with Poisson-like neurons (2 input nodes, 10 hidden nodes and 1 output node). The output activity for the [true, false] and [false, true] inputs becomes stronger, while the output for the [true, true] and [false, false] inputs becomes weak after training. Right: Accumulated administered reward for the four input patterns versus training episode. * Correspondence: joana@neuro.uni-bremen.de Institute for Theoretical Physics, University of Bremen, Bremen, D-28359, Germany © 2011 Vieira et al; licensee BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Vieira et al. BMC Neuroscience 2011, 12(Suppl 1):P250 Page 2 of 2 http://www.biomedcentral.com/1471-2202/12/S1/P250 Published: 18 July 2011 References 1. Sebastian Seung H: Learning in Spiking Neural Networks by Reinforcement of Stochastic Synaptic Transmission. Neuron 2003, 40(6):1063-1073. 2. Xiaohui Xie, Sebastian Seung H: Learning in neural networks by reinforcement of irregular spiking. Phys Rev E 2004, 69(4):041909- 1-041909-10. 3. Schmiedt Joscha T, Christian Albers, Klaus Pawelzik: Spike timing- dependent plasticity as dynamic filter. In Advances in Neural Information Processing Systems 23 J. Lafferty and C. K. I. Williams and J. Shawe-Taylor and R.S. Zemel and A. Culotta 2010, 2110-2118. doi:10.1186/1471-2202-12-S1-P250 Cite this article as: Vieira et al.: Stochastic gradient ascent learning with spike timing dependent plasticity. BMC Neuroscience 2011 12(Suppl 1): P250. Submit your next manuscript to BioMed Central and take full advantage of: • Convenient online submission • Thorough peer review • No space constraints or color figure charges • Immediate publication on acceptance • Inclusion in PubMed, CAS, Scopus and Google Scholar • Research which is freely available for redistribution Submit your manuscript at www.biomedcentral.com/submit http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png BMC Neuroscience Springer Journals

Stochastic gradient ascent learning with spike timing dependent plasticity

Download PDF
2 pages

Loading next page...
 
/lp/springer-journals/stochastic-gradient-ascent-learning-with-spike-timing-dependent-ZlpbIC7NTx

References (6)

Publisher
Springer Journals
Copyright
Copyright © 2011 by Vieira et al; licensee BioMed Central Ltd.
Subject
Biomedicine; Neurosciences; Neurobiology; Animal Models
eISSN
1471-2202
DOI
10.1186/1471-2202-12-S1-P250
Publisher site
See Article on Publisher Site

Abstract

Vieira et al. BMC Neuroscience 2011, 12(Suppl 1):P250 http://www.biomedcentral.com/1471-2202/12/S1/P250 POSTER PRESENTATION Open Access Stochastic gradient ascent learning with spike timing dependent plasticity Joana Vieira , Orlando Arévalo, Klaus Pawelzik From Twentieth Annual Computational Neuroscience Meeting: CNS*2011 Stockholm, Sweden. 23-28 July 2011 Stochastic gradient ascent learning exploits correlations formulation of spike timing dependent plasticity (STDP) of parameter variations with overall success of a system. [3]whenit iscombinedwithareward signal. Here we This algorithmic idea has been related to neuronal net- present conditions under which reward modulated work learning by postulating eligibility traces at STDP is in fact guaranteed to maximize expected synapses, which make them selectable for synaptic reward. We present numerical simulations underlining changes depending on later reward signals ([1] and [2]). the relevance of realistic STDP models for reward Formalizations of the synaptic and neuronal dynamics dependent learning. In particular, we find that the non- supporting gradient ascent learning in terms of differen- linear adaptation to pre- and post-synaptic activities of tial equations exhibit strong similarities with a recent STDP [3] contributes to stable learning. Figure 1 Learning the XOR function with a reward modulated STDP rule. Left: Output activity versus training episode in a feed forward network with Poisson-like neurons (2 input nodes, 10 hidden nodes and 1 output node). The output activity for the [true, false] and [false, true] inputs becomes stronger, while the output for the [true, true] and [false, false] inputs becomes weak after training. Right: Accumulated administered reward for the four input patterns versus training episode. * Correspondence: joana@neuro.uni-bremen.de Institute for Theoretical Physics, University of Bremen, Bremen, D-28359, Germany © 2011 Vieira et al; licensee BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Vieira et al. BMC Neuroscience 2011, 12(Suppl 1):P250 Page 2 of 2 http://www.biomedcentral.com/1471-2202/12/S1/P250 Published: 18 July 2011 References 1. Sebastian Seung H: Learning in Spiking Neural Networks by Reinforcement of Stochastic Synaptic Transmission. Neuron 2003, 40(6):1063-1073. 2. Xiaohui Xie, Sebastian Seung H: Learning in neural networks by reinforcement of irregular spiking. Phys Rev E 2004, 69(4):041909- 1-041909-10. 3. Schmiedt Joscha T, Christian Albers, Klaus Pawelzik: Spike timing- dependent plasticity as dynamic filter. In Advances in Neural Information Processing Systems 23 J. Lafferty and C. K. I. Williams and J. Shawe-Taylor and R.S. Zemel and A. Culotta 2010, 2110-2118. doi:10.1186/1471-2202-12-S1-P250 Cite this article as: Vieira et al.: Stochastic gradient ascent learning with spike timing dependent plasticity. BMC Neuroscience 2011 12(Suppl 1): P250. Submit your next manuscript to BioMed Central and take full advantage of: • Convenient online submission • Thorough peer review • No space constraints or color figure charges • Immediate publication on acceptance • Inclusion in PubMed, CAS, Scopus and Google Scholar • Research which is freely available for redistribution Submit your manuscript at www.biomedcentral.com/submit

Journal

BMC Neuroscience – Springer Journals

Published: Jul 18, 2011

There are no references for this article.