A Tandem Learning Rule for Effective Training and Rapid Inference of Deep Spiking Neural Networks

Abstract

Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures. However, due to the non-differentiable nature of spiking neuronal functions, the standard error back-propagation algorithm is not directly applicable to SNNs. In this work, we propose a tandem learning framework, that consists of an SNN and an Artificial Neural Network (ANN) coupled through weight sharing. The ANN is an auxiliary structure that facilitates the error back-propagation for the training of the SNN at the spike-train level. To this end, we consider the spike count as the discrete neural representation in the SNN, and design ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN. The proposed tandem learning rule demonstrates competitive pattern recognition and regression capabilities on both the conventional frame-based and event-based vision datasets, with at least an order of magnitude reduced inference time and total synaptic operations over other state-of-the-art SNN implementations. Therefore, the proposed tandem learning rule offers a novel solution to training efficient, low latency, and high accuracy deep SNNs with low computing resources.

References in corpus (21)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• WaveNet: A Generative Model for Raw Audio
• Neural Discrete Representation Learning
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Deep Learning in Spiking Neural Networks
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• STDP-based spiking deep convolutional neural networks for object recognition
• SLAYER: Spike Layer Error Reassignment in Time
• A Survey of Neuromorphic Computing and Neural Networks in Hardware
• HFirst: A Temporal Approach to Object Recognition
• Spiking Deep Networks with LIF Neurons
• First-spike based visual categorization using reward-modulated STDP
• Surrogate Gradient Learning in Spiking Neural Networks
• Variational inference for Monte Carlo objectives
• Training Spiking Deep Networks for Neuromorphic Hardware
• Direct Training for Spiking Neural Networks: Faster, Larger, Better
• Spiking Deep Residual Network
• Is Neuromorphic MNIST neuromorphic? Analyzing the discriminative power of neuromorphic datasets in the time domain
• Deep Spiking Networks
• Efficient Computation in Adaptive Artificial Spiking Neural Networks

Cited by in corpus (3)

• Examining the Robustness of Spiking Neural Networks on Non-ideal Memristive Crossbars
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks
• Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition