DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks

TL;DR

DIET-SNN introduces a gradient-trained input encoding method for deep spiking neural networks that optimizes neuron parameters to significantly reduce inference latency and energy consumption while maintaining high accuracy.

Contribution

The paper presents DIET-SNN, a novel approach that directly encodes inputs and optimizes neuron parameters end-to-end, achieving low-latency and energy-efficient SNNs with competitive accuracy.

Findings

Achieves 69% top-1 accuracy on ImageNet with 5 timesteps.

Reduces compute energy by 12x compared to standard ANNs.

Enables 20-500x faster inference than existing SNNs.

Abstract

Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold for each layer of the SNN are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The analog pixel values of an image are directly applied to the input layer of DIET-SNN without the need to convert to spike-train. The first convolutional layer is trained to convert inputs into spikes where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and dense layers of the network. The reduced latency combined with high activation sparsity provides large improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with 5 timesteps (inference latency) on the ImageNet dataset with 12x less compute energy than an equivalent standard ANN. Additionally, DIET-SNN performs 20-500x faster inference compared to other state-of-the-art SNN models.