Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks
This enables rigorous gradient-based learning for spiking neural networks, potentially advancing brain-inspired hardware, though it is incremental as it builds on existing backpropagation methods.
The authors tackled the challenge of applying backpropagation to spiking neural networks by deriving EventProp, an algorithm that computes exact gradients through discrete spike events without approximations, achieving competitive performance on Yin-Yang and MNIST datasets.
Spiking neural networks combine analog computation with event-based communication using discrete spikes. While the impressive advances of deep learning are enabled by training non-spiking artificial neural networks using the backpropagation algorithm, applying this algorithm to spiking networks was previously hindered by the existence of discrete spike events and discontinuities. For the first time, this work derives the backpropagation algorithm for a continuous-time spiking neural network and a general loss function by applying the adjoint method together with the proper partial derivative jumps, allowing for backpropagation through discrete spike events without approximations. This algorithm, EventProp, backpropagates errors at spike times in order to compute the exact gradient in an event-based, temporally and spatially sparse fashion. We use gradients computed via EventProp to train networks on the Yin-Yang and MNIST datasets using either a spike time or voltage based loss function and report competitive performance. Our work supports the rigorous study of gradient-based learning algorithms in spiking neural networks and provides insights toward their implementation in novel brain-inspired hardware.