Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks
Spiking Neural Networks (SNNs) have emerged as a biology-inspired method mimicking the spiking nature of brain neurons. This bio-mimicry derives SNNs' energy efficiency of inference on neuromorphic hardware. However, it also causes an intrinsic disadvantage in training high-performing SNNs from scratch since the discrete spike prohibits the gradient calculation. To overcome this issue, the surrogate gradient (SG) approach has been proposed as a continuous relaxation. Yet the heuristic choice of SG leaves it vacant how the SG benefits the SNN training. In this work, we first theoretically study the gradient descent problem in SNN training and introduce finite difference gradient to quantitatively analyze the training behavior of SNN. Based on the introduced finite difference gradient, we propose a new family of Differentiable Spike (Dspike) functions that can adaptively evolve during training to find the optimal shape and smoothness for gradient estimation. Extensive experiments over several popular network structures show that training SNN with Dspike consistently outperforms the state-of-the-art training methods. For example, on the CIFAR10-DVS classification task, we can train a spiking ResNet-18 and achieve 75.4% top-1 accuracy with 10 time steps.
Code (0)
등록된 구현이 없습니다.
Tasks
Event data classificationImage ClassificationSimilar Papers 제목 키워드 기반
Gradient Descent for Spiking Neural Networks
Much of studies on neural computation are based on network models of static neurons that produce analog output, despite the fact that information processing in the brain is predominantly carried out by dynamic neurons th…
Supervised learning based on temporal coding in spiking neural networks
Gradient descent training techniques are remarkably successful in training analog-valued artificial neural networks (ANNs). Such training techniques, however, do not transfer easily to spiking networks due to the spike g…
RelationSmooth Exact Gradient Descent Learning in Spiking Neural Networks
Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact…
Rethinking Optimization with Differentiable Simulation from a Global Perspective
Differentiable simulation is a promising toolkit for fast gradient-based policy optimization and system identification. However, existing approaches to differentiable simulation have largely tackled scenarios where obtai…
Bayesian OptimizationBeyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
The surrogate gradient descent algorithm enabled spiking neural networks to be trained to carry out challenging sensory processing tasks, an important step in understanding how spikes contribute to neural computations. H…