Fit interpretable models. Explain blackbox machine learning.
-
Updated
Jun 9, 2024 - C++
Fit interpretable models. Explain blackbox machine learning.
A project focusing on binary classification using Explainable Artificial Intelligence (XAI) methods, specifically SHAP (SHapley Additive exPlanations), and Grid Search for hyperparameter tuning. The project utilizes EfficientNetV2-B0 architecture on the Cat VS Dog dataset.
Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.
Explain a black-box module in natural language.
Projeto de Iniciação Científica voltado a ampliar a explicabilidade e transparência dos modelos de Inteligência Artificial atuais. Título Original do Projeto aprovado pelo Edital DIRPE N° 2/2023: Transformando Caixas-Pretas em Caixas de Vidro: Aumentando a Explicabilidade de Redes Neurais com Ferramentas de Visualização e Conversão
AI book for everyone
pytorch implementation of grok
A curated list of awesome responsible machine learning resources.
A curated list of awesome academic research, books, code of ethics, data sets, institutes, newsletters, principles, podcasts, reports, tools, regulations and standards related to Responsible AI, Trustworthy AI, and Human-Centered AI.
moDel Agnostic Language for Exploration and eXplanation
A curated list of awesome NLP, Computer Vision, Model Compression, XAI, Reinforcement Learning, Security etc Paper
An open platform for accelerating the development of eXplainable AI systems
Collection of papers used for a scoping review of explanation types and need indicators in human–agent interact / robotics / human–agent collaborations
Papers about explainability of GNNs
ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
Shapley Interactions for Machine Learning
Advanced AI Explainability for computer vision.All the non Gradient Methods.
Undergraduate Thesis Project
Scripts and trained models from our paper: M. Ntrougkas, N. Gkalelis, V. Mezaris, "T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers", IEEE Access, 2024. DOI:10.1109/ACCESS.2024.3405788.
As part of the Explainable AI Toolkit (XAITK), XAITK-Saliency is an open source, explainable AI framework for visual saliency algorithm interfaces and implementations, built for analytics and autonomy applications.
Add a description, image, and links to the xai topic page so that developers can more easily learn about it.
To associate your repository with the xai topic, visit your repo's landing page and select "manage topics."