Interpretable graph classifications using Graph Convolutional Neural Network

"XAI를 위한 Attribution Method 접근법 분석 및 동향 Analysis and Trend of Attribution Methods for XAI" 에서 사용한 코드와 예시를 공개

Deep_classiflie_db is the backend data system for managing Deep Classiflie metadata, analyzing Deep Classiflie intermediate datasets and orchestrating Deep Classiflie model training pipelines. Deep_classiflie_db includes data scraping modules for the initial model data sources. Deep Classiflie depends upon deep_classiflie_db for much of its anal…

XAI Tutorial for the Explainable AI track in the ALPS winter school 2021

A small repository to test Captum Explainable AI with a trained Flair transformers-based text classifier.

OdoriFy is an open-source tool with multiple prediction engines. This is the source code of the webserver.

Trained Neural Networks (LSTM, HybridCNN/LSTM, PyramidCNN, Transformers, etc.) & comparison for the task of Hate Speech Detection on the OLID Dataset (Tweets).

Training a CNN to recognize the current Go position with photorealistic renders

Interpretability Metrics

This repository contains the source code for Indoor Scene Detector, a full stack deep learning computer vision application.

Overview of different model interpretability libraries.

COVID-19 forecasting model for East Java cities using Joint Learning. My undergrad thesis.

End-to-end toxic Russian comment classification

Model interpretability for Explainable Artificial Intelligence

Collection of NLP model explanations and accompanying analysis tools

Deep Classiflie is a framework for developing ML models that bolster fact-checking efficiency. As a POC, the initial alpha release of Deep Classiflie generates/analyzes a model that continuously classifies a single individual's statements (Donald Trump) using a single ground truth labeling source (The Washington Post). For statements the model d…

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

XAI-Tris

Based on the papers "Interpretability Beyond Feature Attribution: QuantitativeTestingwithConceptActivationVectors(TCAV)" and Captum's instantiation https://captum.ai/docs/captum_insights, we developed this frontend for the Captum project based on the streamlit framework.