machine learning

63-51 : Emerging Technologies / Benoit, Nohen, Thaddée

A customized Pix2Pix implementation for inpainting the headless region of seated Buddha statues found in Anuradhapura, Sri Lanka.

This is a detection model trained on seated Buddha Statue dataset collected from Google Images. The model can be used to detect seated Buddha Statue objects from images under two classes as; Statue head and Statue body. The model is based on YOLO v8

This is a segmentation model trained on seated Buddha Statue dataset collected from Google Images. The model can be used to segment seated Buddha Statue objects from images. The model is based on YOLO v8

Python software for identifying dynamical systems and hidden patterns from time series data

The project focuses on developing a predictive tool for chess using recurrent neural network (RNN) models implemented in TensorFlow. Data collection was carried out using web scraping techniques from the website https://www.chess-poster.com.

El proyecto se orienta hacia el desarrollo de una herramienta predictiva para el ajedrez, empleando modelos de red neuronal recurrente (RNN) implementados en TensorFlow. La recopilación de datos se realizó mediante técnicas de web scraping desde la página https://www.chess-poster.com.

Instance Hardness analysis in Machine Learning

$ mldev | is a data science experiment automation and reproducibility toolkit.

check our experiment templates: https://gitlab.com/mlrep

Automated pipeline for decensoring of doujinshis, using HentAI and DeepCreamPy. Supply an Imgur album link, nhentai link or nhentai id, wait 15-30 minutes, and download significantly decensored images.

This project focuses on extracting and visualizing stock data using Python libraries such as yfinance for historical stock prices and web scraping techniques to gather company revenue data. It provides a comprehensive analysis by plotting both stock prices and revenues over time for companies like Tesla and GameStop.

Research, code, algorithms and all related to artificial intelligence

Notebooks for Pandas, Spark and Python experiments.

Resources for interns and new team members at Tangible AI

This project aims to leverage an extensive dataset of flight booking records sourced from the "Ease My Trip" website to develop predictive models for estimating ticket prices. With a focus on incorporating various influencing factors such as airline choice, travel class, booking lead time, and other significant attributes, our goal is to create a robust analytical framework that enables stakeholders to gain insights into flight pricing dynamics.

This project aims to leverage the Ames Housing Price Dataset to develop an accurate predictive model for estimating residential property sale prices in Ames, Iowa. By analyzing various property features and their relationships to sale prices, the project seeks to uncover insights that can inform both buyers and sellers in the housing market.

This project predicts house prices using machine learning models based on the King County House Sales dataset. It explores Simple Linear, Multiple Linear, Polynomial, and Ridge Regression models, comparing their performance in terms of accuracy. The best model identified is Polynomial Regression, achieving an R² score of 0.75.

This project explores the application of Support Vector Machines (SVM) in classifying human cell records to predict the malignancy of breast cancer samples. By training an SVM model on a dataset of breast cancer features, the goal is to accurately differentiate between benign and malignant cases. This research aims to contribute to the development of early detection and diagnosis methods for breast cancer.