Research map / Optimization / Optimizers
Transparent Classification with Multilayer Logical Perceptrons and Random Binarization
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 CRS instead of the strongest listed baseline | classification on the 12 UCI datasets · Average | Macro F1: 86.82 -> 86.98 | Helped |
| Train MLLP without Random Binarization (ablation) | CRS learning · Average | Macro F1: 86.98 -> 84.40 | Hurt |
| Extract discrete CRS without training with Random Binarization (ablation) | CRS · Average | Macro F1: 86.98 -> 47.31 | Hurt |
| Apply Random Binarization at an appropriate rate (about 0.7 to 0.9) | deep CRS · Connect-4 | Macro F1 | Helped |
| Apply Random Binarization | shallow CRS · Connect-4 | Macro F1 | No clear effect |
| Set the binarization rate too close to 1.0 (ablation) | CRS · Connect-4 | Macro F1 | Hurt |
| Increase width at the same depth (ablation) | CRS · Connect-4 | Macro F1 | Helped |
| Apply dead-node detection and redundant-rule elimination (ablation) | CRS · 12 UCI datasets | number of edges | Helped |
Closest papers by meaning
- Learning Accurate and Interpretable Decision Rule Sets from Neural Networks (AAAI 2021 · similarity 0.84)
- Neural-based classification rule learning for sequential data (ICLR 2023 · similarity 0.82)
- Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations (NeurIPS 2018 · similarity 0.82)
- Generalized Convergence Analysis of Tsetlin Automaton Based Algorithms: A Probabilistic Approach to Concept Learning (AAAI 2025 · similarity 0.81)
- Differentiable Rule Induction from Raw Sequence Inputs (ICLR 2025 · similarity 0.80)
- MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes (CVPR 2024 · similarity 0.80)
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.