Implementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.
-
Updated
Aug 25, 2021 - Python
Implementation of the Integrated Directional Gradients method for Deep Neural Network model explanations.
A set of notebooks as a guide to the process of fine-grained image classification of birds species, using PyTorch based deep neural networks.
Bachelor's thesis for degree in Economics at HSE University, Saint-Petersburg (2022)
⛈️ Code for the paper "End-to-End Prediction of Lightning Events from Geostationary Satellite Images"
The official repo for the EACL 2023 paper "Quantifying Context Mixing in Transformers"
Materials for the Lab "Explaining Neural Language Models from Internal Representations to Model Predictions" at AILC LCL 2023 🔍
Feature Attribution methods for neurons and Evolution experiments
Collection of NLP model explanations and accompanying analysis tools
Counterfactual SHAP: a framework for counterfactual feature importance
Code and data for the ACL 2023 NLReasoning Workshop paper "Saliency Map Verbalization: Comparing Feature Importance Representations from Model-free and Instruction-based Methods" (Feldhus et al., 2023)
Explainable AI in Julia.
Codes for the paper On marginal feature attributions of tree-based models
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.
Materials for "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" at ICLR'24 🐑 🐑
Model interpretability and understanding for PyTorch
Reproducible code for our paper "Explainable Learning with Gaussian Processes"
Add a description, image, and links to the feature-attribution topic page so that developers can more easily learn about it.
To associate your repository with the feature-attribution topic, visit your repo's landing page and select "manage topics."