A new biologically plausible supervised learning method for spiking neurons
作者： Ammar Belatreche , Aboozar Taherkhani , Liam P. Maguire , Yuhua Li
DOI:
关键词: Depolarization 、 Supervised learning 、 Spike train 、 Neuron response 、 Computer science 、 Machine learning 、 Artificial intelligence
摘要: STDP is believed to play an important role in learning and memory. Additionally, experimental evidence shows that a few strong neural inputs can drive neuron response subsequently affect the of other inputs. Furthermore, recent studies have shown local dendritic depolarization impact induction. This paper integrates these three biological concepts devise new biologically plausible supervised method for spiking neurons. Experimental results show proposed effectively map random spatiotemporal input pattern target output spike train with much faster speed than ReSuMe.
ulster.ac.uk参考文章(10)
Yan Xu, Xiaoqin Zeng, Lixin Han, Jing Yang, A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks Neural Networks. ,vol. 43, pp. 99- 113 ,(2013) , 10.1016/J.NEUNET.2013.02.003
Yves Fr�gnac, Daniel E. Shulz, Activity-dependent regulation of receptive field properties of cat area 17 by supervised Hebbian learning. Journal of Neurobiology. ,vol. 41, pp. 69- 82 ,(1999) , 10.1002/(SICI)1097-4695(199910)41:1<69::AID-NEU10>3.0.CO;2-1
J. J. Letzkus, B. M. Kampa, G. J. Stuart, Learning Rules for Spike Timing-Dependent Plasticity Depend on Dendritic Synapse Location The Journal of Neuroscience. ,vol. 26, pp. 10420- 10429 ,(2006) , 10.1523/JNEUROSCI.2650-06.2006
Daniel E. Feldman, The spike-timing dependence of plasticity. Neuron. ,vol. 75, pp. 556- 571 ,(2012) , 10.1016/J.NEURON.2012.08.001
Nikola Kasabov, Kshitij Dhoble, Nuttapod Nuntalid, Giacomo Indiveri, 2013 Special Issue: Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition Neural Networks. ,vol. 41, pp. 188- 201 ,(2013) , 10.1016/J.NEUNET.2012.11.014
Abigail Morrison, Markus Diesmann, Wulfram Gerstner, Phenomenological models of synaptic plasticity based on spike timing Biological Cybernetics. ,vol. 98, pp. 459- 478 ,(2008) , 10.1007/S00422-008-0233-1
S. Schreiber, J.M. Fellous, D. Whitmer, P. Tiesinga, T.J. Sejnowski, A new correlation-based measure of spike timing reliability Neurocomputing. ,vol. 52, pp. 925- 931 ,(2003) , 10.1016/S0925-2312(02)00838-X
Jun Hu, Huajin Tang, K. C. Tan, Haizhou Li, Luping Shi, A spike-timing-based integrated model for pattern recognition Neural Computation. ,vol. 25, pp. 450- 472 ,(2013) , 10.1162/NECO_A_00395
Filip Ponulak, Andrzej Kasiński, Supervised learning in spiking neural networks with resume: Sequence learning, classification, and spike shifting Neural Computation. ,vol. 22, pp. 467- 510 ,(2010) , 10.1162/NECO.2009.11-08-901
Sander M. Bohte, Joost N. Kok, Han La Poutré, Error-backpropagation in temporally encoded networks of spiking neurons Neurocomputing. ,vol. 48, pp. 17- 37 ,(2000) , 10.1016/S0925-2312(01)00658-0