AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Understanding Deep Architecture with Reasoning Layer

Xinshi Chen, Yufei Zhang, Christoph Reisinger, Le Song

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 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
Use a faster-converging reasoning algorithmHybrid perception-and-reasoning architecture · Synthetic experimentsapproximation accuracyImproved
Use NAG instead of GDHybrid architecture with quadratic energy · Synthetic experimentsapproximation accuracyImproved
Increase the reasoning-layer depthHybrid architecture with an over- or under-parameterized neural module · Synthetic experiments and BSD500 denoisinggeneralization gapHurt
Increase the reasoning-layer depthHybrid architecture with an about-right neural-module parameterization · Synthetic experiments and BSD500 denoisinggeneralization gapMixed
Use a more stable algorithm layer, such as GD rather than NAGHybrid architecture with an over- or under-parameterized neural module · BSD500 denoisinggeneralization gapImproved
Use a faster-converging algorithm layer, such as NAG rather than GDHybrid architecture with an about-right neural-module parameterization · Generalization analysisgeneralization gapMixed
Replace a traditional algorithm layer with an RNN reasoning layerHybrid architecture · Synthetic learning-to-optimize experimentsgeneralization abilityHurt
Replace a traditional algorithm layer with an RNN reasoning layerHybrid architecture · Synthetic learning-to-optimize experimentsrepresentation powerImproved

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