Efficient learning with augmented spikes: A case study with image classification.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Efficient learning of spikes plays a valuable role in training spiking neural networks (SNNs) to have desired responses to input stimuli. However, current learning rules are limited to a binary form of spikes. The seemingly ubiquitous phenomenon of burst in nervous systems suggests a new way to carry more information with spike bursts in addition to times. Based on this, we introduce an advanced form, the augmented spikes, where spike coefficients are used to carry additional information. How could neurons learn and benefit from augmented spikes remains unclear. In this paper, we propose two new efficient learning rules to process spatiotemporal patterns composed of augmented spikes. Moreover, we examine the learning abilities of our methods with a synthetic recognition task of augmented spike patterns and two practical ones for image classification. Experimental results demonstrate that our rules are capable of extracting information carried by both the timing and coefficient of spikes. Our proposed approaches achieve remarkable performance and good robustness under various noise conditions, as compared to benchmarks. The improved performance indicates the merits of augmented spikes and our learning rules, which could be beneficial and generalized to a broad range of spike-based platforms.

Authors

  • Shiming Song
    Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, 300350, China.
  • Chenxiang Ma
    Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, 300350, China.
  • Wei Sun
    Sutra Medical Inc, Lake Forest, CA.
  • Junhai Xu
    School of Computer Science and Technology, Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin University, Tianjin 300350, PR China.
  • Jianwu Dang
    School of Electronic & Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China.
  • Qiang Yu
    State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau, Northwest A&F University, Yangling 712100, China; College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China. Electronic address: yuq@nwsuaf.edu.cn.