Hyperdimensional Decoding of Spiking Neural Networks

TL;DR

This paper introduces a new decoding method combining spiking neural networks with hyperdimensional computing, achieving higher accuracy, robustness, and lower energy consumption than existing methods.

Contribution

The paper presents a novel SNN-HDC decoding approach that improves classification accuracy, reduces latency, and lowers energy use, also capable of identifying unseen classes.

Findings

Achieved 1.24x to 3.67x energy reduction on DvsGesture dataset.

Achieved 1.38x to 2.27x energy reduction on SL-Animals-DVS dataset.

Can identify 100% of samples from unseen classes in DvsGesture.

Abstract

This work presents a novel spiking neural network (SNN) decoding method, combining SNNs with Hyperdimensional computing (HDC). The goal is to create a decoding method with high accuracy, high noise robustness, low latency and low energy usage. Compared to analogous architectures decoded with existing approaches, the presented SNN-HDC model attains generally better classification accuracy, lower classification latency and lower estimated energy consumption on multiple test cases from literature. The SNN-HDC achieved estimated energy consumption reductions ranging from 1.24x to 3.67x on the DvsGesture dataset and from 1.38x to 2.27x on the SL-Animals-DVS dataset. The presented decoding method can also efficiently identify unknown classes it has not been trained on. In the DvsGesture dataset the SNN-HDC model can identify 100% of samples from an unseen/untrained class. Given the numerous benefits shown and discussed in this paper, this decoding method represents a very compelling alternative to both rate and latency decoding.