AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Bullet Trains: Parallelizing Training of Temporally Precise Spiking Neural Networks

Todd Morrill, Christian-Gernot Pehle, Anthony M. Zador

ICML 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
process input spikes in parallel chunks with associative scans instead of seriallyevent-based LIF SNN with exact hard reset · SHD training time per batchspeedup: up to 44.27xImproved
increase hidden layer size and batch size (ablation)parallel SNN · SHDspeedup over serial: 44.27x -> 7.95xHurt
increase chunk size beyond ~128 (ablation)parallel SNN · SHD runtimebatch runtimeMixed
use continuous spike times with numerical solvers instead of analytical tau_m=2tau_sexact-gradient SNN · MNIST 1F350Haccuracy: 97.20 -> 98.04Improved
use continuous spike times and delays vs discrete-time exact gradientsexact-gradient SNN 2F512HD · SSCaccuracy: 76.10 -> 77.79Improved
use continuous-time exact gradients instead of surrogate gradient with discrete timeSNN with delays · SSCaccuracy: 80.69 -> 77.79Hurt
quantize spike times to larger time steps (ablation)Yin-Yang ITD task · Yin-Yangtest accuracy: near chance (33%) at dt >= 2msHurt
use Newton-Raphson instead of Bisection solver (ablation)spike time solver · convergenceiterations to precision: Bisection needs 20 iterationsImproved
use fixed logit temperature multiplier for weighted leaky integrator output (ablation)output layer logits · classificationstability of softmaxImproved

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