Training Deep Spiking Neural Networks using Backpropagation
This work addresses the problem of efficient and accurate training of SNNs for researchers and practitioners in neuromorphic computing, offering a direct method that improves performance on event-based vision tasks.
The paper tackles the challenge of training deep spiking neural networks (SNNs) by introducing a novel technique that treats membrane potentials as differentiable signals, enabling direct error backpropagation on spike signals. This approach outperforms all previous methods on the permutation invariant MNIST and N-MNIST benchmarks, achieving state-of-the-art results.
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable nature of asynchronous spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are only considered as noise. This enables an error backpropagation mechanism for deep SNNs, which works directly on spike signals and membrane potentials. Thus, compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statics of spikes more precisely. Our novel framework outperforms all previously reported results for SNNs on the permutation invariant MNIST benchmark, as well as the N-MNIST benchmark recorded with event-based vision sensors.