AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

GPEX, A Framework For Interpreting Artificial Neural Networks

Amir Akbarnejad, Gilbert Bigras, Nilanjan Ray

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability · 2 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 GPEX instead of representer point selection for label correctiondataset debugging · Cifar10 automobile vs horseinstances shown to reach about 90% accuracy: 7000 -> 4000Improved
use GPEX instead of influence functions for label correctiondataset debugging · Cifar10 automobile vs horseinstances shown to reach about 90% accuracy: 7000 -> 4000Improved
use influence functions instead of GPEX for spotting corrupted labelsdataset debugging · Cifar10 automobile vs horsecorrupted labels found per instances shownHurt
use GPEX instead of representer point selection for spotting corrupted labelsdataset debugging · Cifar10 automobile vs horsecorrupted labels found per instances shownImproved
smaller dataset with few inducing pointsGPEX on DogsWolves · DogsWolvesPearson correlation between GP mean and ANNHurt
apply GPEX to attention submodulesGPEX · Cifar10, MNIST, KatherPearson correlation between GP mean and ANNImproved

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