Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance

Abstract

Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency. Unfortunately, its development has fallen far behind the conventional deep neural network (DNN), mainly because of difficult training and lack of widely accepted hardware experiment platforms. In this paper, we show that a deep temporal-coded SNN can be trained easily and directly over the benchmark datasets CIFAR10 and ImageNet, with testing accuracy within 1% of the DNN of equivalent size and architecture. Training becomes similar to DNN thanks to the closed-form solution to the spiking waveform dynamics. Considering that SNNs should be implemented in practical neuromorphic hardwares, we train the deep SNN with weights quantized to 8, 4, 2 bits and with weights perturbed by random noise to demonstrate its robustness in practical applications. In addition, we develop a phase-domain signal processing circuit schematic to implement our spiking neuron with 90% gain of energy efficiency over existing work. This paper demonstrates that the temporal-coded deep SNN is feasible for applications with high performance and high energy efficient.

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Deep Learning in Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• Ternary Weight Networks
• A CMOS Spiking Neuron for Brain-Inspired Neural Networks with Resistive Synapses and In-Situ Learning
• Training Spiking Deep Networks for Neuromorphic Hardware
• Direct Training for Spiking Neural Networks: Faster, Larger, Better
• Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data
• Encoding Spike Patterns in Multilayer Spiking Neural Networks
• Differentiable Fine-grained Quantization for Deep Neural Network Compression
• Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection

Cited by in corpus (2)

• Deep Residual Learning in Spiking Neural Networks
• Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding