SLAYER: Spike Layer Error Reassignment in Time
This addresses the challenge of low-power spike-based computation for neuromorphic hardware, representing a novel method rather than an incremental improvement.
The authors tackled the problem of training deep Spiking Neural Networks (SNNs) by introducing a new backpropagation mechanism that overcomes the non-differentiability of spike functions, achieving state-of-the-art performance on datasets like MNIST, NMNIST, DVS Gesture, and TIDIGITS.
Configuring deep Spiking Neural Networks (SNNs) is an exciting research avenue for low power spike event based computation. However, the spike generation function is non-differentiable and therefore not directly compatible with the standard error backpropagation algorithm. In this paper, we introduce a new general backpropagation mechanism for learning synaptic weights and axonal delays which overcomes the problem of non-differentiability of the spike function and uses a temporal credit assignment policy for backpropagating error to preceding layers. We describe and release a GPU accelerated software implementation of our method which allows training both fully connected and convolutional neural network (CNN) architectures. Using our software, we compare our method against existing SNN based learning approaches and standard ANN to SNN conversion techniques and show that our method achieves state of the art performance for an SNN on the MNIST, NMNIST, DVS Gesture, and TIDIGITS datasets.