AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

A Classification of $G$-invariant Shallow Neural Networks

Devanshu Agrawal, James Ostrowski

NeurIPS 2022 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 3 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
allow type 2 (signed permutation) architectures beyond ordinary permutation-representation (type 1) onesG-invariant shallow neural network architectures · D4 on four elementsnumber of architectures: five type 1 vs seven type 2Improved
use signed instead of unsigned permutation representation for C6 hidden layerC6-invariant SNN · C6 permutation representationtopology of architectureMixed
let bias go to zero in the type 1 architectureC6 rotation type 1 SNN · 2D rotation representation of C6function-space distance to type 2Mixed

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