AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data

Wanli Hong, Shuyang Ling

JMLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 9 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
increase data dimension d/n at low noise (sigma=0.18)two-layer ReLU network · GMM, K=2NC1: below 10^{-4} except d/n=1.1Improved
increase noise sigma to 0.8 or moretwo-layer ReLU network · GMM, K=2NC1Hurt
widen first layer d1three-layer network with fixed first layer · FMnist, K=10NC1-NC3: order of 10^{-3} for d1=2*10^4Improved

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