Direct Training of SNN using Local Zeroth Order Method

Bhaskar Mukhoty · Velibor Bojkovic · William de Vazelhes · Xiaohan Zhao · Giulia De Masi · Huan Xiong · Bin Gu

Great Hall & Hall B1+B2 (level 1) #519
[ ]
Thu 14 Dec 8:45 a.m. PST — 10:45 a.m. PST


Spiking neural networks are becoming increasingly popular for their low energy requirement in real-world tasks with accuracy comparable to traditional ANNs. SNN training algorithms face the loss of gradient information and non-differentiability due to the Heaviside function in minimizing the model loss over model parameters. To circumvent this problem, the surrogate method employs a differentiable approximation of the Heaviside function in the backward pass, while the forward pass continues to use the Heaviside as the spiking function. We propose to use the zeroth-order technique at the local or neuron level in training SNNs, motivated by its regularizing and potential energy-efficient effects and establish a theoretical connection between it and the existing surrogate methods. We perform experimental validation of the technique on standard static datasets (CIFAR-10, CIFAR-100, ImageNet-100) and neuromorphic datasets (DVS-CIFAR-10, DVS-Gesture, N-Caltech-101, NCARS) and obtain results that offer improvement over the state-of-the-art results. The proposed method also lends itself to efficient implementations of the back-propagation method, which could provide 3-4 times overall speedup in training time. The code is available at \url{}.

Chat is not available.