Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks

PATTERN RECOGNITION

卷:94

Article

Mozafari, Milad¹  Ganjtabesh, Mohammad¹  Nowzari-Dalini, Abbas¹  Thorpe, Simon J.²  Masquelier, Timothee² 

[1] Univ Tehran, Sch Math Stat & Comp Sci, Dept Comp Sci, Tehran, Iran

[2] Univ Toulouse 3, CNRS, UMR 5549, CERCO, Toulouse, France

关键词: Spiking neural networks;    Deep architecture;    Digit recognition;    STDP;    Reward-modulated STDP;    Latency coding;   

DOI  :  10.1016/j.patcog.2019.05.015

来源: Elsevier

【 摘 要 】

The primate visual system has inspired the development of deep artificial neural networks, which have revolutionized the computer vision domain. Yet these networks are much less energy-efficient than their biological counterparts, and they are typically trained with backpropagation, which is extremely data-hungry. To address these limitations, we used a deep convolutional spiking neural network (DCSNN) and a latency-coding scheme. We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lower layers and reward-modulated STDP (R-STDP) for the higher ones. In short, with R-STDP a correct (resp. incorrect) decision leads to STDP (resp. anti-STDP). This approach led to an accuracy of 97.2% on MNIST, without requiring an external classifier. In addition, we demonstrated that R-STDP extracts features that are diagnostic for the task at hand, and discards the other ones, whereas STDP extracts any feature that repeats. Finally, our approach is biologically plausible, hardware friendly, and energy-efficient. (C) 2019 Elsevier Ltd. All rights reserved.

【 授权许可】

Free