Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

TL;DR

This paper introduces TSSL-BP, a novel backpropagation method for deep spiking neural networks that improves temporal learning accuracy and efficiency, enabling high-performance image classification with fewer time steps.

Contribution

The paper proposes TSSL-BP, a new training algorithm that effectively handles spiking discontinuities and inter/intra-neuron dependencies, reducing the required time steps for training deep SNNs.

Findings

TSSL-BP improves accuracy on CIFAR10 dataset.

It reduces the number of time steps needed for training.

The method enhances temporal learning precision in deep SNNs.

Abstract

Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors. However, existing SNN error backpropagation (BP) methods lack proper handling of spiking discontinuities and suffer from low performance compared with the BP methods for traditional artificial neural networks. In addition, a large number of time steps are typically required to achieve decent performance, leading to high latency and rendering spike-based computation unscalable to deep architectures. We present a novel Temporal Spike Sequence Learning Backpropagation (TSSL-BP) method for training deep SNNs, which breaks down error backpropagation across two types of inter-neuron and intra-neuron dependencies and leads to improved temporal learning precision. It captures inter-neuron dependencies through presynaptic firing times by considering the all-or-none characteristics of firing activities and captures intra-neuron dependencies by handling the internal evolution of each neuronal state in time. TSSL-BP efficiently trains deep SNNs within a much shortened temporal window of a few steps while improving the accuracy for various image classification datasets including CIFAR10.