Obstacle to training SpikeProp networks: cause of surges in training process

Authors:
Takase Haruhiko;Fujita Masaru;Kawanaka Hiroharu;Tsuruoka Shinji;Kita Hidehiko;Hayashi Terumine
Affiliations:
Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan;Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan;Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan;Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan;Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan;Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 1
Cited 3

Lower bounds for the computational power of networks of spiking neurons

Neural Computation

Supervised Learning of Logical Operations in Layered Spiking Neural Networks with Spike Train Encoding

Neural Processing Letters
A spike-timing-based integrated model for pattern recognition

Neural Computation
Supervised learning in multilayer spiking neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we discuss an obstacle to training in SpikeProp[1], which is a type of supervised learning algorithms for spiking neural networks. In the original publication of SpikeProp, weights with mixed signs are suspected to cause failures of training. We pointed out the cause of it through some experiments. Weights with mixed signs make the dynamics of the unit's activity twisted, and the twisted dynamics break the assumption that SpikeProp algorithm is based on. Therefore, it causes surges in training processes. They would mean an underlying problem on training processes.