Supervised Learning in Temporally-Coded Spiking Neural Networks with Approximate Backpropagation
This addresses the challenge of efficient training for spiking neural networks, which is incremental as it builds on existing methods but offers computational improvements.
The authors tackled the problem of supervised learning in temporally-coded spiking neural networks by proposing a new method that mimics backpropagation with less computation, achieving performance matching a comparable non-spiking network on MNIST digit classification.
In this work we propose a new supervised learning method for temporally-encoded multilayer spiking networks to perform classification. The method employs a reinforcement signal that mimics backpropagation but is far less computationally intensive. The weight update calculation at each layer requires only local data apart from this signal. We also employ a rule capable of producing specific output spike trains; by setting the target spike time equal to the actual spike time with a slight negative offset for key high-value neurons the actual spike time becomes as early as possible. In simulated MNIST handwritten digit classification, two-layer networks trained with this rule matched the performance of a comparable backpropagation based non-spiking network.