AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Stable learning using spiking neural networks equipped with affine encoders and decoders

A. Martina Neuman, Dominik Dold, Philipp Christian Petersen

JMLR 2025 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 4 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
restrict spiking-layer synaptic weights to positive values (affine SNN) instead of positive and negative (ablation)Affine SNN reproducing a shallow ReLU network · Teacher ReLU regression (d0=40, M=20)test lossImproved
use affine SNN instead of a deep ReLU network for small training setsAffine SNN, quadratic regression · Quadratic regression (5 to 10000 samples)test lossImproved
use affine SNN instead of a deep ReLU network on Yin-Yang classificationAffine SNN, Yin-Yang · Yin-Yang classificationtest lossNo clear effect

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