Fit interpretable models. Explain blackbox machine learning.
-
Updated
Jun 1, 2024 - C++
Fit interpretable models. Explain blackbox machine learning.
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 interpretability and understanding for PyTorch
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
Code associated wth the InterpretE research paper
A curated list of awesome responsible machine learning resources.
Learning active instances on the border in the case of imbalanced data classification task.
Implementation of Beyond Neural Scaling beating power laws for deep models and prototype-based models
A PyTorch implementation of constrained optimization and modeling techniques
An end-to-end implementation of Breast Cancer Detection using prosemble ML package within the fastapi framework with deployment on Heroku platform as a service cloud.
An end-to-end implementation of Breast Cancer Detection using prosemble ML package within the Flask framework integrated in PyWebIO with deployment on Heroku platform as a service cloud.
A collection of research materials on explainable AI/ML
NAISR: A 3D Neural Additive Model for Interpretable Shape Representation
SIDU: SImilarity Difference and Uniqueness method for explainable AI
Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.
Final Year Project Try-Out Codes
JAX-based Model Explanation and Interpretation Library
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
AI Division, Reverse Engineering CNN Trojans
ICCV2021 paper: Interpretable Image Recognition by Constructing Transparent Embedding Space (TesNet)
Add a description, image, and links to the interpretable-ai topic page so that developers can more easily learn about it.
To associate your repository with the interpretable-ai topic, visit your repo's landing page and select "manage topics."