AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Densely Connected G-invariant Deep Neural Networks with Signed Permutation Representations

Devanshu Agrawal, James Ostrowski

JMLR 2023 · Architectures and efficiency › RNNs and normalization · approach: Symmetry and equivariance in loss landscapes · 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
use type 2 signed perm-irreps instead of type 1G-DNN · binary multiplication (m=16)classification accuracy: 50% -> 100%Improved
use type 2 signed perm-irreps instead of type 1G-DNN · binary multiplication (m=16)final binary cross-entropy loss: 0.71 -> 0.00Improved
replace constrained G-DNN by the larger unraveled architecture (about 6.5x parameters)G-DNN type 2 · binary multiplication (m=16)classification accuracy: 100% -> 50%Hurt
initialize unraveled architecture with type 2 initial weightsunraveled architecture · binary multiplication (m=16)final loss: 11.36 -> 1.33 initial loss; final 0.71 -> 0.70No clear effect
use G-DNN skip-connected architecture instead of CReLUarchitecture space · icosahedral group admissible architecturesnumber of admissible architectures: 2639 -> 4751Improved
use G-DNN instead of CReLU at depth 9architecture space · icosahedral groupadmissible architectures: 0 -> 80Improved
use G-DNN instead of CReLU at depth 4architecture space · group C2^3, |G|=8admissible fraction: 238/392 -> 392/392Improved
use G-DNN instead of CReLU at depth 3architecture space · group C2^3, |G|=8admissible fraction: 88/434 -> 93/434Improved
use G-DNN instead of CReLU at depth 4architecture space · group C2xC4, |G|=8admissible fraction: 34/48 -> 48/48Improved
use G-DNN instead of CReLU for cyclic C8 and Q8architecture space · groups C8 and Q8admissible fraction: 9/9 -> 9/9 at depth 2 for Q8No clear effect
use mixed architecture with type 1 and type 2 signed perm-irreps instead of type 1 or unraveled onlyG-DNN · ModelNet40 validationvalidation accuracyImproved

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