A stochastic approach to STDP
作者： Runchun Wang , Chetan Singh Thakur , Tara Julia Hamilton , Jonathan Tapson , Andre van Schaik
DOI: 10.1109/ISCAS.2016.7538989
关键词:
摘要: We present a digital implementation of the Spike Timing Dependent Plasticity (STDP) learning rule. The proposed consists an exponential decay (exp-decay) generator array and STDP adaptor array. weight values are stored in memory, w ill send these to exp-decay using spike which duration is modulated according values. will then generate decay, be used by for performing adaption. computational expensive, efficiently implemented novel stochastic approach. This approach was fully analysed characterised. use time multiplexing achieve 8192 (8k) virtual adaptors generators with only one physical respectively. have validated our measurement results balanced excitation experiment. In that experiment, competition (induced STDP) between synapses can establish bimodal distribution synaptic weights: either towards zero (weak) or maximum (strong) Our therefore ideal implementing rule large-scale spiking neural networks running real time.
harvard.edu
arxiv.org
sci-hub.se 参考文章(14)
Donald O. Hebb, The organization of behavior Neurocomputing: foundations of research. pp. 43- 54 ,(1988)
Sen Song, Kenneth D. Miller, L. F. Abbott, Competitive Hebbian learning through spike-timing-dependent synaptic plasticity Nature Neuroscience. ,vol. 3, pp. 919- 926 ,(2000) , 10.1038/78829
Runchun M. Wang, Tara J. Hamilton, Jonathan C. Tapson, André van Schaik, A neuromorphic implementation of multiple spike-timing synaptic plasticity rules for large-scale neural networks. Frontiers in Neuroscience. ,vol. 9, pp. 180- 180 ,(2015) , 10.3389/FNINS.2015.00180
Runchun Wang, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik, A compact neural core for digital implementation of the Neural Engineering Framework biomedical circuits and systems conference. pp. 548- 551 ,(2014) , 10.1109/BIOCAS.2014.6981784
Runchun Wang, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik, A compact reconfigurable mixed-signal implementation of synaptic plasticity in spiking neurons international symposium on circuits and systems. pp. 862- 865 ,(2014) , 10.1109/ISCAS.2014.6865272
Tara Julia Hamilton, Saeed Afshar, Andre van Schaik, Jonathan Tapson, Stochastic Electronics: A Neuro-Inspired Design Paradigm for Integrated Circuits Proceedings of the IEEE. ,vol. 102, pp. 843- 859 ,(2014) , 10.1109/JPROC.2014.2310713
G. Indiveri, E. Chicca, R. Douglas, A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity IEEE Transactions on Neural Networks. ,vol. 17, pp. 211- 221 ,(2006) , 10.1109/TNN.2005.860850
Runchun Wang, Gregory Cohen, Klaus M. Stiefel, Tara Julia Hamilton, Jonathan Tapson, André van Schaik, An FPGA implementation of a polychronous spiking neural network with delay adaptation Frontiers in Neuroscience. ,vol. 7, pp. 14- 14 ,(2013) , 10.3389/FNINS.2013.00014
Saeed Afshar, Libin George, Chetan Singh Thakur, Jonathan Tapson, Andre van Schaik, Philip de Chazal, Tara Julia Hamilton, Turn Down That Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron IEEE Transactions on Biomedical Circuits and Systems. ,vol. 9, pp. 188- 196 ,(2015) , 10.1109/TBCAS.2015.2416391
Runchun M. Wang, Tara J. Hamilton, Jonathan C. Tapson, André van Schaik, A mixed-signal implementation of a polychronous spiking neural network with delay adaptation. Frontiers in Neuroscience. ,vol. 8, pp. 51- 51 ,(2014) , 10.3389/FNINS.2014.00051