Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible with Various Temporal Codes

Chaofei Hong, Xile Wei, Jiang Wang, Bin Deng, Haitao Yu, Yanqiu Che

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Recent studies have demonstrated the effectiveness of supervised learning in spiking neural networks (SNNs). A trainable SNN provides a valuable tool not only for engineering applications but also for theoretical neuroscience studies. Here, we propose a modified SpikeProp learning algorithm, which ensures better learning stability for SNNs and provides more diverse network structures and coding schemes. Specifically, we designed a spike gradient threshold rule to solve the well-known gradient exploding problem in SNN training. In addition, regulation rules on firing rates and connection weights are proposed to control the network activity during training. Based on these rules, biologically realistic features such as lateral connections, complex synaptic dynamics, and sparse activities are included in the network to facilitate neural computation. We demonstrate the versatility of this framework by implementing three well-known temporal codes for different types of cognitive tasks, namely, handwritten digit recognition, spatial coordinate transformation, and motor sequence generation. Several important features observed in experimental studies, such as selective activity, excitatory-inhibitory balance, and weak pairwise correlation, emerged in the trained model. This agreement between experimental and computational results further confirmed the importance of these features in neural function. This work provides a new framework, in which various neural behaviors can be modeled and the underlying computational mechanisms can be studied.

Original languageEnglish (US)
Article number8743403
Pages (from-to)1285-1296
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume31
Issue number4
DOIs
StatePublished - Apr 2020

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible with Various Temporal Codes'. Together they form a unique fingerprint.

Cite this