PyTorch-based tools for visualizing and understanding the neurons of a GAN.
-
Updated
Dec 8, 2018 - Python
PyTorch-based tools for visualizing and understanding the neurons of a GAN.
This repository contains an implementation of DISC, an algorithm for learning DFAs for multiclass sequence classification.
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
Implementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.
The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".
Genetic programming method for explaining complex black-box models
Investigate BERT on Non-linearity and Layer Commutativity
A baseline genetic algorithm for the discovery of counterfactuals, implemented in Python for ease of use and heavily leveraging NumPy for speed.
Concept activation vectors for Keras
Optimal Sparse Decision Trees
Explaining Model Behavior with Global Causal Analysis
Decision Trees to understand CNNs. Project for Neural Networks 2020 course at Sapienza.
A Python package implementing a new interpretable machine learning model for text classification (with visualization tools for Explainable AI )
[NeurIPS 2023] This is the official code for the paper "TPSR: Transformer-based Planning for Symbolic Regression"
Measuring Biases in Masked Language Models for PyTorch Transformers. Support for multiple social biases and evaluation measures.
PIP-Net: Patch-based Intuitive Prototypes Network for Interpretable Image Classification (CVPR 2023)
The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classification"
An Open-Source Library for the interpretability of time series classifiers
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Add a description, image, and links to the interpretable-ml topic page so that developers can more easily learn about it.
To associate your repository with the interpretable-ml topic, visit your repo's landing page and select "manage topics."