Timezone: »

 
Poster
Theoretically Provable Spiking Neural Networks
Shao-Qun Zhang · Zhi-Hua Zhou

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #924
in Poster Session 5 »

Spiking neural networks have attracted increasing attention in recent years due to their potential of handling time-dependent data. Many algorithms and techniques have been developed; however, theoretical understandings of many aspects of spiking neural networks are far from clear. A recent work [Zhang and Zhou, 2021] disclosed that typical spiking neural networks could hardly work on spatio-temporal data due to their bifurcation dynamics and suggested that the self-connection structure has to be added. In this paper, we theoretically investigate the approximation ability and computational efficiency of spiking neural networks with self connections, and show that the self-connection structure enables spiking neural networks to approximate discrete dynamical systems using a polynomial number of parameters within polynomial time complexities. Our theoretical results may shed some insight for the future studies of spiking neural networks.

Keywords: spiking neural networks · Computational Efficiency · Self Connection · Continuous Dynamical Systems · Approximation Power
[ Paper]  [ Slides]  [ OpenReview] 

Author Information

Shao-Qun Zhang (Nanjing University)
Zhi-Hua Zhou (Nanjing University)

More from the Same Authors