The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition

TL;DR

This paper introduces a hierarchical, brain-inspired Spiking Neural Network system called Spiking Gating Flow (SGF) for online gesture recognition, achieving high accuracy with minimal training data and epochs.

Contribution

The paper presents a novel hierarchical SNN architecture with a gating mechanism, demonstrating superior accuracy and efficiency in gesture recognition compared to existing non-backpropagation methods.

Findings

Achieved 87.5% accuracy on DVS gesture classification benchmark.

Required only a single training epoch for learning.

Outperformed other non-backpropagation SNNs in accuracy.

Abstract

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in the emerging industrial fields such as robotic visions and automobiles. However, current deep learning faces major challenges for such applications because of the huge computational cost and the inefficient learning. Hence, we develop a novel brain-inspired Spiking Neural Network (SNN) based system titled Spiking Gating Flow (SGF) for online action learning. The developed system consists of multiple SGF units which assembled in a hierarchical manner. A single SGF unit involves three layers: a feature extraction layer, an event-driven layer and a histogram-based training layer. To demonstrate the developed system capabilities, we employ a standard Dynamic Vision Sensor (DVS) gesture classification as a benchmark. The results indicate that we can achieve 87.5% accuracy which is comparable with Deep Learning (DL), but at smaller training/inference data number ratio 1.5:1. And only a single training epoch is required during the learning process. Meanwhile, to the best of our knowledge, this is the highest accuracy among the non-backpropagation algorithm based SNNs. At last, we conclude the few-shot learning paradigm of the developed network: 1) a hierarchical structure-based network design involves human prior knowledge; 2) SNNs for content based global dynamic feature detection.