Research map / Architectures and efficiency / RNNs and normalization
Learning to Reason with Third Order Tensor Products
Imanol Schlag, Jürgen Schmidhuber
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use TPR-RNN instead of SDNC | bAbI all-tasks model · bAbI all-tasks test | Avg Error: 6.4 ± 2.5 -> 1.34 ± 0.52 | Improved |
| Use TPR-RNN instead of REN | bAbI single-task model · bAbI single-task test | Avg Error: 0.5 -> 0.17 | Improved |
| Train on entity-task pairs with systematic gaps in coverage | TPR-RNN · bAbI systematic generalisation test | accuracy | Improved |
| Add the move operation to write-only memory (ablation) | TPR-RNN · bAbI single-task test | Failed tasks (err > 5%) | Improved |
| Add the backlink operation to write-only memory (ablation) | TPR-RNN · bAbI single-task test | Failed tasks (err > 5%) | Improved |
| Add the move operation to write-plus-backlink memory (ablation) | TPR-RNN · bAbI single-task test | Failed tasks (err > 5%) | No clear effect |
Closest papers by meaning
- Neural-Symbolic Recursive Machine for Systematic Generalization (ICLR 2024 · similarity 0.85)
- Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace (NeurIPS 2026 · similarity 0.84)
- On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study (NeurIPS 2025 · similarity 0.84)
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach (NeurIPS 2025 · similarity 0.84)
- An Evaluation of Approaches to Train Embeddings for Logical Inference (Student Abstract) (AAAI 2025 · similarity 0.84)
- Neuro-Symbolic Temporal Point Processes (ICML 2024 · similarity 0.84)
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.
