Predicting probability of default (at 12 months from observation) for small companies

Just a lib converting HCI communication dumps to Cypress chips into LiME memory dumps. !!! Migrated to Codeberg 🏔️ !!!

Interpretability of Image Keras Models

TIC is a library that acts as a Toolbox for Interpretability Comparison.

Deep learning solution for explaining and detecting emotions in advertisement videos.

Repository for the journal article 'SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction'

TeleXGI: Explainable Gastrointestinal Image Classification for TeleSurgery Systems

eXplainable Artificial Intelligence - Squeezing LIME in a custom network & SHAPling around a custom network

An explainability model that can be applied to BERT-based Turkish sentiment analysis models has been developed and its performance has been compared with model spesific Layer-wise relevance propogation expailanbility model of Hila Chefer.

Analyze CV with XAI

Explainable AI for underwater acoustic models.

A library to read and write LiME files/blobs in python

A web application that detects aggression and misogyny in text using BERT augmentation, sentiment analysis, XGBoost, TF-IDF vectorization, LIME explainability. [Paper accepted at ICON 2021]

Pytorch Implementation of the Interpretable Conditional Adversarial Autoencoder using LIME (ICASSP 2024)

Applying GradCAM method with 3 kinds of CNN-based model for NLP classification task on french dataset.

SLICE: Stabilized LIME for Consistent Explanations for Image Classification

This repository explores the use of eXplainable AI (XAI) to interpret deep learning models in underwater SONAR image classification. We utilize transfer learning with CNN architectures like VGG16 and ResNet50, and apply LIME and SP-LIME for transparent model explanations.

Designed a Machine Learning model which takes newsgroup dataset and performs binary classification to predict if a given document has Atheistic or Christian sentiment. Used LIME library and PySpark. Performed feature selection to improve classifier’s performance.