Saved in:
Bibliographic Details
Main Authors: Kinavuidi, Cedrick, Peres, Luca, Rhodes, Oliver
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910157974274048
author Kinavuidi, Cedrick
Peres, Luca
Rhodes, Oliver
author_facet Kinavuidi, Cedrick
Peres, Luca
Rhodes, Oliver
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08558
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hyperdimensional Decoding of Spiking Neural Networks
Kinavuidi, Cedrick
Peres, Luca
Rhodes, Oliver
Artificial Intelligence
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.
title Hyperdimensional Decoding of Spiking Neural Networks
topic Artificial Intelligence
url https://arxiv.org/abs/2511.08558