88 Open source projects that are alternatives of or similar to Captum

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

Techniques & resources for training interpretable ML models, explaining ML models, and debugging ML models.

Fit interpretable models. Explain blackbox machine learning.

A curated list of awesome machine learning interpretability resources.

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

Collection of NLP model explanations and accompanying analysis tools

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

Sample use case for Xavier AI in Healthcare conference: https://www.xavierhealth.org/ai-summit-day2/

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

Many Class Activation Map methods implemented in Pytorch for CNNs and Vision Transformers. Including Grad-CAM, Grad-CAM++, Score-CAM, Ablation-CAM and XGrad-CAM

Visualization toolkit for neural networks in PyTorch! Demo -->

Federated Learning Library: https://fedml.ai

Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)

Layer-wise Relevance Propagation (LRP) for LSTMs

Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.

A collection of tools for reverse engineering neural networks.

Code for the TCAV ML interpretability project

H2O.ai Machine Learning Interpretability Resources

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

深度学习近年来关于神经网络模型解释性的相关高引用/顶会论文(附带代码)

Human-explainable AI.

A collection of research materials on explainable AI/ML

A curated list of awesome Fairness in AI resources

💡 A curated list of adversarial attacks on model explanations

A lightweight implementation of removal-based explanations for ML models.

In this part, I've introduced and experimented with ways to interpret and evaluate models in the field of image. (Pytorch)

A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.

Awesome Resources for Advanced Computer Vision Topics

XAI - An eXplainability toolbox for machine learning

📍 Interactive Studio for Explanatory Model Analysis

Interesting resources related to XAI (Explainable Artificial Intelligence)

Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.

Public facing deeplift repo

A Python package implementing a new machine learning model for text classification with visualization tools for Explainable AI

A collection of infrastructure and tools for research in neural network interpretability.

🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

StellarGraph - Machine Learning on Graphs

General Interpretability Package

A library for finding knowledge neurons in pretrained transformer models.

Automatic equation building and curve fitting. Runs on Tensorflow. Built for academia and research.

A set of notebooks as a guide to the process of fine-grained image classification of birds species, using PyTorch based deep neural networks.

Code for SPINE - Sparse Interpretable Neural Embeddings. Jhamtani H.*, Pruthi D.*, Subramanian A.*, Berg-Kirkpatrick T., Hovy E. AAAI 2018

Text classification models. Used a submodule for other projects.

Towards Understanding Deep Learning Representations via Interactive Experimentation

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

In this project I aim to apply Various Predictive Maintenance Techniques to accurately predict the impending failure of an aircraft turbofan engine.

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

A game theoretic approach to explain the output of any machine learning model.

[ECCV 2018] code for Choose Your Neuron: Incorporating Domain Knowledge Through Neuron Importance

Pytorch Implementation of recent visual attribution methods for model interpretability

Codebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.

🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations

For calculating global feature importance using Shapley values.

Algorithms for monitoring and explaining machine learning models

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

⬛ Python Individual Conditional Expectation Plot Toolbox

[ICCV 2017] Torch code for Grad-CAM

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code.