AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Learning to Reason with Third Order Tensor Products

Imanol Schlag, Jürgen Schmidhuber

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 25 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 TPR-RNN instead of SDNCbAbI all-tasks model · bAbI all-tasks testAvg Error: 6.4 ± 2.5 -> 1.34 ± 0.52Improved
Use TPR-RNN instead of RENbAbI single-task model · bAbI single-task testAvg Error: 0.5 -> 0.17Improved
Train on entity-task pairs with systematic gaps in coverageTPR-RNN · bAbI systematic generalisation testaccuracyImproved
Add the move operation to write-only memory (ablation)TPR-RNN · bAbI single-task testFailed tasks (err > 5%)Improved
Add the backlink operation to write-only memory (ablation)TPR-RNN · bAbI single-task testFailed tasks (err > 5%)Improved
Add the move operation to write-plus-backlink memory (ablation)TPR-RNN · bAbI single-task testFailed tasks (err > 5%)No clear effect

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