Research map / Architectures and efficiency / RNNs and normalization
Learning to Teach
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use a learned adaptive data-selection policy instead of NoTeach | LSTM · IMDB | accuracy: 88.54% -> 89.46% | Helped |
| use a learned adaptive data-selection policy instead of SPL | LSTM · IMDB | accuracy: 88.80% -> 89.46% | Helped |
| remove model features from the teacher state (ablation) | L2T · MNIST | convergence | Hurt |
| remove combined data-and-learner features from the teacher state (ablation) | L2T · MNIST | convergence | Hurt |
| remove data features from the teacher state (ablation) | L2T · MNIST | convergence | Hurt |
Closest papers by meaning
- Iterative Teacher-Aware Learning (NeurIPS 2021 · similarity 0.88)
- Learning to Teach with Dynamic Loss Functions (NeurIPS 2018 · similarity 0.88)
- Machine Teaching of Active Sequential Learners (NeurIPS 2019 · similarity 0.86)
- Teaching to Learn: Sequential Teaching of Learners with Internal States (AAAI 2023 · similarity 0.86)
- Iterative Classroom Teaching (AAAI 2019 · similarity 0.86)
- Towards an AI Course Based on Neural Networks (AAAI 2025 · similarity 0.85)
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.