Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons Article Swipe

MAKE IMPACT

Sidi Yaya Arnaud Yarga , Sean U. N. Wood · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2306.12666

Spiking neural networks (SNN) are able to learn spatiotemporal features while using less energy, especially on neuromorphic hardware. The most widely used spiking neuron in deep learning is the Leaky Integrate and Fire (LIF) neuron. LIF neurons operate sequentially, however, since the computation of state at time t relies on the state at time t-1 being computed. This limitation is shared with Recurrent Neural Networks (RNN) and results in slow training on Graphics Processing Units (GPU). In this paper, we propose the Stochastic Parallelizable Spiking Neuron (SPSN) to overcome the sequential training limitation of LIF neurons. By separating the linear integration component from the non-linear spiking function, SPSN can be run in parallel over time. The proposed approach results in performance comparable with the state-of-the-art for feedforward neural networks on the Spiking Heidelberg Digits (SHD) dataset, outperforming LIF networks while training 10 times faster and outperforming non-spiking networks with the same network architecture. For longer input sequences of 10000 time-steps, we show that the proposed approach results in 4000 times faster training, thus demonstrating the potential of the proposed approach to accelerate SNN training for very large datasets.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2306.12666

PDF

https://arxiv.org/pdf/2306.12666

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4381827072

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4381827072

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2306.12666

Digital Object Identifier

Title

Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-06-22

Full publication date if available

Authors

Sidi Yaya Arnaud Yarga, Sean U. N. Wood

List of authors in order

Landing page

https://arxiv.org/abs/2306.12666

Publisher landing page

PDF URL

https://arxiv.org/pdf/2306.12666

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2306.12666

Direct OA link when available

Concepts

Spiking neural network, Parallelizable manifold, Computer science, Neuromorphic engineering, Artificial intelligence, Artificial neural network, Graphics, Feed forward, Algorithm, Computer graphics (images), Engineering, Control engineering

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload