AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays

Roel Koopman, Sebastian Otte, Sander Bohte

NeurIPS 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes SpikingGamma, an online SNN training method using smoothed temporal delays to achieve temporally precise spiking under fine time discretization.

Problem

Training spiking neural networks under fine temporal discretization is difficult, which hinders low-latency responsiveness and mapping software-trained SNNs to efficient neuromorphic hardware.

Approach

Uses smoothed temporal delays for online SNN training, as an alternative to modeling spiking neurons as self-recurrent units embedded in recurrent networks; the abstract is truncated so the exact mechanism is not fully stated.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy