Supervised learning in spiking, neural networks with noise-threshold

NEUROCOMPUTING

卷:219

Article

Zhang, Malu¹  Qu, Hong¹  Xie, Xiurui¹  Kurths, Juergen^2,3,4 

[1] Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China

[2] Potsdam Inst Climate Impact Res PIK, D-14473 Potsdam, Germany

[3] Humboldt Univ, Dept Phys, D-12489 Berlin, Germany

[4] Univ Aberdeen, Inst Complex Syst & Math Biol, Aberdeen AB24 3UE, Scotland

关键词: Spiking neurons;    Noise-threshold;    Supervised learning;    Spiking neural networks (SNNs);    Anti-noise capability;   

DOI  :  10.1016/j.neucom.2016.09.044

来源: Elsevier

【 摘 要 】

With a similar capability of processing spikes as biological neural systems, networks of spiking neurons are expected to achieve a performance similar to that of living brains. Despite the achievement of spiking neuron based applications, most of them assume noise-free condition for learning and testing. This assumption, though fairly general, ignores the fact that noise widely exists in spiking neural networks (SNNs) and the neural response can be significantly disturbed by noise. Therefore, how to deal with noise is an important issue in the applications of SNNs. Here, by analyzing strategies employed to make spiking neurons robust to noise, also inspired by biological neurons, we propose a strategy that train spiking neurons with a dynamic firing threshold named noise-threshold. The noise-threshold can be applied by the existing supervised learning methods to improve the noise tolerance of them. Experimental results show that, with a combination of noise-threshold, the anti-noise capability of the existing supervised learning methods improves significantly, and the trained neuron can precisely and reliably reproduce target sequences of spikes even under highly noisy conditions. More importantly, the SNNs-based computational model equipped with a noise-threshold is more robust and can achieve a good performance even with different types of noise. Therefore, the noise-threshold is significant to practical applications and theoretical researches of SNNs.

【 授权许可】

Free