Research map / Architectures and efficiency / RNNs and normalization
Learning Accurate and Interpretable Decision Rule Sets from Neural Networks
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 DR-Net rather than the other interpretable rule learners | DR-Net · magic, adult, heloc, and house | test accuracy (%) | Helped |
| Use DR-Net rather than black-box RF or DNN models | DR-Net · magic, adult, heloc, and house | test accuracy (%) | Mixed |
| Optimize model complexity rather than average rule complexity with the sparsity penalty | DR-Net · magic, adult, heloc, and house | model complexity | Mixed |
| Use DR-Net across increasing complexity settings rather than competing rule learners | DR-Net · magic, adult, and house | test accuracy | Helped |
| Use DR-Net rather than RIPPER on heloc | DR-Net · heloc | test accuracy | Mixed |
Closest papers by meaning
- Deep Neural Networks Constrained by Decision Rules (AAAI 2019 · similarity 0.90)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.87)
- Neural Reasoning Networks: Efficient Interpretable Neural Networks with Automatic Textual Explanations (AAAI 2025 · similarity 0.87)
- HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets (NeurIPS 2024 · similarity 0.87)
- Factor Graph-based Interpretable Neural Networks (ICLR 2025 · similarity 0.84)
- Data-Efficient Learning with Neural Programs (NeurIPS 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.