AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation

Anastasis Kratsios, Cody Hyndman

JMLR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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
add NEU feature map to the DNNDNN · Apple stock tracker, testMSE: 5.112289 -> 4.948565Improved
add NEU feature map to elastic netENET · Apple stock tracker, testMSE: 4.903049 -> 5.369902Hurt
add NEU feature map to kernel ridgekRidge · Apple stock tracker, testMSE: 5.110043 -> 5.515611Hurt
add NEU feature map to gradient boosted random forestsGBRF · Apple stock tracker, testMSE: 5.971403 -> 5.989319No clear effect
add NEU feature map to the auto-encoder (1 factor)AE · US bond yield curve, testMSE: 14.792091 -> 11.043391Improved
add NEU feature map to the auto-encoder (2 factors)AE · US bond yield curve, testMSE: 11.930328 -> 10.425360Improved
add NEU feature map to the auto-encoder (3 factors)AE · US bond yield curve, testMSE: 14.688698 -> 13.579660Improved
add NEU feature map to PCA (3 factors)PCA · US bond yield curve, testMSE: 15.176116 -> 14.439484Improved
add NEU feature map to PCA (1 factor)PCA · US bond yield curve, testMSE: 15.302093 -> 15.518402No clear effect
add NEU feature map to kernel PCA (2 factors)kPCA · US bond yield curve, testMSE: 15.614535 -> 21.080980Hurt
add NEU feature map to kernel ridgekRidge · Simulation, jump discontinuity, testMSE: 0.088674 -> 0.074313Improved
add NEU feature map to DNNDNN · Simulation, aperiodic oscillations, testMSE: 0.304498 -> 0.296543Improved

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