Title: A supervised learning algorithm based on spike train inner products for recurrent spiking neural networks

Authors: Xianghong Lin; Xiaomei Pi; Xiangwen Wang

Addresses: College of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, 730070, China ' College of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, 730070, China ' College of Computer Science and Engineering, Northwest Normal University, Lanzhou, Gansu, 730070, China

Abstract: For recurrent spiking neural networks (RSNNs), constructing an efficient supervised learning algorithms is difficult because of their complex recurrent structure and an implicit nonlinear spike firing mechanism. This paper presents a supervised learning algorithm based on spike train inner products in RSNNs. The proposed algorithm transforms the discrete spike train into a continuous function using a special kernel function, and we design the corresponding error function for the backpropagation process. The proposed algorithm is successfully applied to spike train learning and pattern classification problems. The experimental results show that our algorithm has higher accuracy than the algorithm for feedback-based online local learning of weights (FOLLOW). Therefore, it is an effective method to solve the spatio-temporal pattern learning problems.

Keywords: supervised learning; RSNNs; recurrent spiking neural networks; spike train inner product; kernel function.

DOI: 10.1504/IJCSM.2023.131629

International Journal of Computing Science and Mathematics, 2023 Vol.17 No.4, pp.309 - 319

Received: 24 Oct 2021
Received in revised form: 04 Jan 2022
Accepted: 17 Aug 2022
Published online: 21 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article