AI Paper Atlas

Research map / Large language models / AI and society

Bridging Machine Learning and Logical Reasoning by Abductive Learning

NeurIPS 2019 · Large language models › AI and society · approach: Social-science view of AI evaluation · 89 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
abductive learning (CNN + logical abduction) vs end-to-end neural netshandwritten equation decipherment · DBA and RBAaccuracyHelped
train ABL on only length 5-8 equations (ABL-short) instead of all (ablation)ABL · DBA and RBAaccuracyNo clear effect
abductive learning with logic background knowledge vs CNNextended n-queens · MNIST chessboardsaccuracy: 0.736 ± 0.016 -> 0.981 ± 0.006Helped
abductive learning vs Bi-LSTMextended n-queens · MNIST chessboardsaccuracy: 0.513 ± 0.013 -> 0.976 ± 0.008Helped
swap abduction engine (ALP, CHR, CLP(FD)) (ablation)ABL · extended n-queensaccuracy: 0.976 / 0.979 / 0.981No clear effect
transfer CNN learned on DBA (perception transfer) (ablation)ABL · XOR equationsconvergence speedHelped
transfer knowledge model from RBA to DBA (ablation)ABL · DBAconvergence speedHelped
ABL vs human volunteersequation classification · DBA and RBAaccuracyHelped

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