Skip to content
AI News HubLIVE
Original source2 min read

Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks

Summary

A new preprint combines several biologically motivated spike-encoding schemes with Rouser adaptive-threshold surrogate gradients and K-FAC second-order optimization, showing on MNIST and Fashion-MNIST that these methods can improve spiking neural network accuracy and parameter efficiency without increasing model size.

SourcearXiv Machine LearningAuthor: Ayaan Qayyum, Bruce Yi Bu, Zicong Li, Jingfeng Zhou
Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks

View a PDF of the paper titled Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks, by Ayaan Qayyum and 3 other authors

View PDF HTML (experimental)

Abstract:Spiking Neural Networks (SNNs) offer theoretical energy-efficiency advantages over conventional deep networks, but realizing these advantages on vision tasks requires sparse spike representations that naive rate-coding methods fail to provide. We combine biologically motivated spike-encoding schemes with two training improvements: Rouser adaptive-threshold surrogate gradients and Kronecker-Factored Approximate Curvature (K-FAC) second-order optimization. The spike encoding schemes experimented with are rate coding, latency coding, DVS-style delta modulation, and Difference-of-Gaussians (DoG) filtering. Experiments on MNIST and Fashion-MNIST demonstrate that biologically inspired encoders yield the largest accuracy gains in capacity-constrained regimes and serve as an effective parameter-efficiency lever. DoG and delta modulation encoders produce significantly sparser spike trains than rate coding. K-FAC yields modest but consistent accuracy improvements over Adam-trained baselines, and Rouser's learnable per-neuron thresholds improve Fashion-MNIST accuracy from 87.37% to 88.13% by enabling homeostatic firing-rate regulation. Biologically grounded pre-processing methods can help close the accuracy gap between SNNs and non-spiking baselines without increasing model size.

Comments: 17 pages, 9 figures

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.23242 [cs.LG]

(or arXiv:2611.23242v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.23242

arXiv-issued DOI via DataCite

Submission history

From: Ayaan Qayyum [view email] [v1] Wed, 2 Sep 2026 23:26:09 UTC (6,485 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks, by Ayaan Qayyum and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Difference-of-Gaussians and DVS-style delta modulation encoders produce much sparser spike trains than rate coding.
  • Rouser's learnable per-neuron thresholds lift Fashion-MNIST accuracy from 87.37% to 88.13% via homeostatic firing-rate regulation.
  • K-FAC delivers modest but consistent gains over Adam-trained baselines.
  • Biologically inspired encoders yield the largest gains under capacity constraints, helping close the gap with non-spiking networks.

Highlights and analysis are generated automatically and may contain errors. Check the original source.