Obstacle to training SpikeProp networks — Cause of surges in training process —
Haruhiko Takase, Masaru Fujita, Hiroharu Kawanaka, Shinji Tsuruoka, Hidehiko Kita, Terumine Hayashi · 2009
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.