The main idea for this project is explore a Kaggle dataset about ChatGPT reviews using a NLP approach in order to apply ML models for score reviews predictions. I applied LIME algorithm to evaluate explainability about text classifiers. Should it be possible to apply complex network? Let's try.

Sushi online delivery shop project with typescript / redux toolkit

A solid foundational understanding of XAI, primarily emphasizing how XAI methodologies can expose latent biases in datasets and reveal valuable insights.

Feature Engineering, Regression, Classification, Model Explanation. My 2 biggest projects exploring the link between economic indicators and U.S. presidential election results.

Qt-DAB, a general software DAB (DAB+) decoder with a (slight) focus on showing the signal

Explaining black boxes with a SMILE: Statistical Mode-agnostic Interpretability with Local Explanations

Performed model evaluation using evaluation metrics such as accuracy, precision, recall, F1-score etc. Then model interpretation using feature importance, SHAP and LIME. Finally , evaluated model robustness and stability through techniques like bootstrapping or Monte Carlo simulations.

Implementation of LIME focused on producing user-centric local explanations for image classifiers.

Developing delivery time estimation model using Neural Networks

A V-slice fork/engine made to have modding in mind. Built off of V-Slice's Source Code

This repository contains the Python scripts that I have written and run to execute a series of analytic model developments using datasets taken from the book "The Elements of Statistical Elements" by Hastie, Tibshirani, Friedman

Multicycles.org aggregates on one map, more than 300 share vehicles like bikes, scooters, mopeds and cars. Demo APP for the Data Flow API, see https://flow.fluctuo.com

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

Classifying Travel Mode choice in the Netherlands using KNN, XGBoost, RF and TabNet

A tool for classifying an image into a disaster type, utilizing Python

A library for drawing graphics on the console screen

C# LIME protocol implementation

Unpack, Pack & Resign files encrypted with the 1st version of "Lime" encryption.

Scripts for generating SHAP & LIME explainations and their corresponding plots

This repository provides the training codes to classify aerial images using a custom-built model (transfer learning with InceptionResNetV2 as the backbone) and explainers to explain the predictions with LIME and GradCAM on an interface that lets you upload or paste images for classification and see visual explanations.