interpret_with_rules
Rule induction tool
This project provides tools to induce rules from trained neural networks to explain model predictions and data patterns.
Code for the paper "Rule induction for global explanation of trained models"
21 stars
12 watching
7 forks
Language: Python
last commit: 4 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 scikit-learn-contrib/skope-rules | A Python machine learning module that generates logical rules to predict class labels with high precision | 625 |
 elastic/detection-rules | Provides a set of reusable code components for developing and testing security rules | 1,966 |
 jwieting/acl2017 | A codebase for training and using models of sentence embeddings. | 33 |
 jianbo-lab/l2x | A Python framework for learning to interpret models using information-theoretic methods | 124 |
 tmadl/sklearn-expertsys | A scikit-learn wrapper for interpretable classifiers based on decision rules | 489 |
 xiaoqijiao/coling2018 | Provides training and testing code for a CNN-based sentence embedding model | 2 |
 interpretml/dice | Provides counterfactual explanations for machine learning models to facilitate interpretability and understanding. | 1,364 |
 wojciechz/learning_to_execute | This software trains an LSTM-based neural network to predict Python code snippets | 480 |
 blent-ai/alepython | An ALE plot generation tool for explaining machine learning model predictions | 158 |
 ujjwalkarn/datasciencepython | A curated list of tutorials and resources for learning Python for data science, machine learning, and other related topics. | 5,274 |
 eli5-org/eli5 | A Python package for debugging and explaining predictions of machine learning classifiers | 262 |
 nlprinceton/alacarte | Tools and code for inducing custom semantic vector representations from text data | 104 |
 christophm/rulefit | An algorithm implementation for rule-based prediction using gradient boosting and L1 regularization. | 411 |
 atmb4u/data-driven-code | Code examples for a data-driven approach to building neural networks in Python | 29 |
| jwieting/iclr2016 | Code for training universal paraphrastic sentence embeddings and models on semantic similarity tasks | 193 |