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

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.

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Training Deep Nets with Sublinear Memory Cost
• SLAYER: Spike Layer Error Reassignment in Time
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• Surrogate Gradient Learning in Spiking Neural Networks
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• Exploring the Connection Between Binary and Spiking Neural Networks
• Direct Training for Spiking Neural Networks: Faster, Larger, Better
• Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
• Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
• Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networks

Cited by in corpus (12)

• Deep Residual Learning in Spiking Neural Networks
• TCL: an ANN-to-SNN Conversion with Trainable Clipping Layers
• IMPULSE: A 65nm Digital Compute-in-Memory Macro with Fused Weights and Membrane Potential for Spike-based Sequential Learning Tasks
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• Spiking neural networks trained via proxy
• Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression
• Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning
• HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification
• Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation
• One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency
• Event-Enhanced Multi-Modal Spiking Neural Network for Dynamic Obstacle Avoidance
• HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise