AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning Interpretable Rules for Scalable Data Representation and Classification

Zhuo Wang, Wei Zhang, Ning Liu, Jianyong Wang

TPAMI 2023 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 58 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
add novel logical activation functions (NLAF) instead of original ones (ablation)RRL with Gradient Grafting · activity and fashion (large)training lossImproved
add novel logical activation functions (NLAF) (ablation)RRL with Gradient Grafting · facebook (sparse, large)training lossNo clear effect
add novel logical activation functions (NLAF) (ablation)RRL · GPU memory and timeGPU memory / timeImproved
use Gradient Grafting instead of STE (ablation)RRL (NLAF) · six data setstraining lossImproved
use Gradient Grafting instead of ProxQuant or Random Binarization (ablation)RRL (NLAF) · six data setstraining lossImproved
add hierarchical Gradient Grafting instead of single grafting (ablation)deep RRL · two data sets, 3-4 logical layerstraining lossImproved
increase logical layers from one or two to three (hierarchical grafting) (ablation)RRL · two data setstraining lossImproved
RRL versus XGBoostRRL · 14 datasetsaverage rank: 2.50 vs 3.50Improved
RRL versus CRSRRL · facebookF1 macro (%): 90.11 vs 11.38Improved
RRL versus C4.5RRL · 14 datasetsaverage rank: 2.50 vs 11.57Improved
RRL versus XGBoost on fashionRRL · fashionF1 macro (%): 89.64 vs 89.82Hurt
RRL versus transformers FT and SAINT on tic-tac-toeRRL · tic-tac-toeF1 macro (%): 100.0 vs 97.84 and 96.95Improved

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