Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks

by   Jibin Wu, et al.

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the training of deep SNNs is not straightforward. In this paper, we propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition, which is referred to as progressive tandem learning of deep SNNs. By studying the equivalence between ANNs and SNNs in the discrete representation space, a primitive network conversion method is introduced that takes full advantage of spike count to approximate the activation value of analog neurons. To compensate for the approximation errors arising from the primitive network conversion, we further introduce a layer-wise learning method with an adaptive training scheduler to fine-tune the network weights. The progressive tandem learning framework also allows hardware constraints, such as limited weight precision and fan-in connections, to be progressively imposed during training. The SNNs thus trained have demonstrated remarkable classification and regression capabilities on large-scale object recognition, image reconstruction, and speech separation tasks, while requiring at least an order of magnitude reduced inference time and synaptic operations than other state-of-the-art SNN implementations. It, therefore, opens up a myriad of opportunities for pervasive mobile and embedded devices with a limited power budget.


page 6

page 10

page 14


A Tandem Learning Rule for Efficient and Rapid Inference on Deep Spiking Neural Networks

Emerging neuromorphic computing (NC) architectures have shown compelling...

Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks

Spiking neural networks (SNNs) are biology-inspired artificial neural ne...

Closing the Accuracy Gap in an Event-Based Visual Recognition Task

Mobile and embedded applications require neural networks-based pattern r...

Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection

Spiking Neural Networks (SNNs) have garnered widespread interest for the...

Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision

Event-based vision sensors encode local pixel-wise brightness changes in...

Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation

Over the past decade, artificial neural networks (ANNs) have made tremen...

ReStoCNet: Residual Stochastic Binary Convolutional Spiking Neural Network for Memory-Efficient Neuromorphic Computing

In this work, we propose ReStoCNet, a residual stochastic multilayer con...

Please sign up or login with your details

Forgot password? Click here to reset