A method for conditional shapley value estimation, built off the shapr package: https://github.com/NorskRegnesentral/shapr/tree/master

Explanations gain more and more attention in the context of explainable systems. This repo contains research about different aspects of explanations and how to integrate them in an existing system.

code for paper in NLDB'23

End-to-end ML: Using ML to generate expected PPS, opportunity grade classification, and prescription analysis for basketball coaches.

Análisis de modelos de Deep Learning mediante SHAP values. Desarrollo y programación de herramientas que permitan interpretar modelos de Deep Learning usando las SHAP values, generando una mejor explicación de los factores en los que se basa el modelo a la hora de tomar sus predicciones.

Training and inference code for text classification models

JAX-based Model Explanation and Interpretation Library

Official repository of the paper titled Explaining models relating objects and privacy and accepted at The 3rd Explainable AI for Computer Vision (XAI4CV) Workshop at CVPR 2024

Code for the paper: P2ExNet: Patch-based Prototype Explanation Network

A simple tutorial for the Template System for Natural Language Explanations

This repository accompanies my research into the interpretability of DNA Damage Repair Outcome Predictors (DROPs). By analyzing these models using interpretability methods, we hope to uncover what features specifically are driving the accuracy of these prediction models.

This repository is an implementation of the paper "Trustworthy Medical Image Segmentation with improved performance for in-distribution samples" published in Neural Networks.

Visualizing 3D ResNet for Medical Image Classification With Score-CAM

Optimising Rule Extraction for Deep Neural Networks. My third year university dissertation project

What and How of Machine Learning Transparency – ECML-PKDD 2020 Hands-on Tutorial

A doctoral dissertation titled "Towards the Advancement of Open-Domain Textual Question Answering Methods". The dissertation presents several innovative solutions aimed at addressing the challenges faced by ODQA systems and improving the performance.

Training and exploration of linear probes into Othello-GPT by Li et al. (2022)

Adaptation of the official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks [CVPR 2021] to ESM.

Extracting finite state machine (Mealy Machine) from Recurrent Neural Networks (Many-to-Many)

1.The polymer-units(repeating units) are identified from the SMILES code of the polymer