rogerbaiges
I'm an Artificial Intelligence Student at UPC with a focus on machine learning, deep learning, and AI algorithms.
Barcelona
Pinned Repositories
bicing-optimization-local-search
This repository seeks to optimize bikes distribution of a public bicycle renting service across city stations using local search algorithms like Hill Climbing and Simulated Annealing, aiming to minimize costs and efficiently meet demand. It includes tools to visualize the distribution and showcases the utility of AI in urban logistics.
challenge-auditoria
Project to detect inventory impairment in any company dataset using AI. Its goal is making the work of the auditors easier and it was the winning project of the Challenge IA i Auditoria in the Col·legi de Censors Jurats de Comptes de Catalunya.
hackupc-2024
top-streaming-songs-modeling
This repository contains the PMAAD course project from the Artificial Intelligence Degree at Universitat Politècnica de Catalunya. It models and analyzes Spotify's top 40 weekly streamed songs (2017-2021) using R. Techniques include clustering, textual analysis, and geospatial analysis to uncover music trends and characteristics.
CatGPT
CatGPT is a Catalan-specific language model, trained from scratch with 111 million parameters. Designed for educational purposes, it provides a simple tool to explore Catalan natural language processing.
LanguageDetector
The "Language Detection Using Character Trigrams and LID" project excels in identifying the language of text with over 99.89% F1-score accuracy, using statistical NLP. It leverages character trigrams and Lidstone's Law for precise language detection, supporting multiple languages including English, Spanish, Italian, Dutch, German, and French.
MLP-Model-Improvement-Project
opinion-detector
The Opinion Detector project provides tools to automatically classify movie reviews as positive or negative. Using a mix of machine learning models, it analyzes text to detect sentiments. The project stands out for its use of both supervised models, like Logistic Regression, and unsupervised methods using Lesk and sentiwordnet.
rogerbaiges
Config files for my GitHub profile.
simplex-optimization-algorithm
The project implements the Simplex algorithm in Python, focusing on solving linear optimization problems. It introduces a structured approach with two primary classes: Problem, which stores problem details, and Simplex, which performs the optimization. Emphasizing adaptability, it supports loading data from external files and incorporates numpy.
rogerbaiges's Repositories
rogerbaiges/simplex-optimization-algorithm
The project implements the Simplex algorithm in Python, focusing on solving linear optimization problems. It introduces a structured approach with two primary classes: Problem, which stores problem details, and Simplex, which performs the optimization. Emphasizing adaptability, it supports loading data from external files and incorporates numpy.
rogerbaiges/LanguageDetector
The "Language Detection Using Character Trigrams and LID" project excels in identifying the language of text with over 99.89% F1-score accuracy, using statistical NLP. It leverages character trigrams and Lidstone's Law for precise language detection, supporting multiple languages including English, Spanish, Italian, Dutch, German, and French.
rogerbaiges/MLP-Model-Improvement-Project
rogerbaiges/opinion-detector
The Opinion Detector project provides tools to automatically classify movie reviews as positive or negative. Using a mix of machine learning models, it analyzes text to detect sentiments. The project stands out for its use of both supervised models, like Logistic Regression, and unsupervised methods using Lesk and sentiwordnet.
rogerbaiges/rogerbaiges
Config files for my GitHub profile.
rogerbaiges/SurvivalPredictionCirrhosis
The "SurvivalPredictionCirrhosis" project uses machine learning to predict cirrhosis patient survival, supporting clinical decisions. It includes data cleaning, feature analysis, and models like KNN, Decision Trees, SVM, Random Forest, XGBoost, and EBM, with a focus on accuracy and interpretability.