Projects
This section aims to contain the description of the most significant projects I have been a part of, as well as the ongoing projects that currently occupy my time and expertise.
Oct 18, 2023
This project represents my master's thesis for a Computer Science degree at the University of Trento. It pioneers an interactive debugging protocol merging Interactive Machine Learning and Neuro-Symbolic AI. It introduces a multi-round approach for comprehensive model debugging, automatically extracting relevant arguments, and facilitating user-machine dialogues. With successful bug correction, argument selection, and identification of confounding sources, it sets the stage for enhanced interactive debugging in complex machine learning models.
Nov 22, 2022
PSO-OpenMPI is a project developed specifically for the High Performance Computing for Data Science course as part of the Master's Degree program in Computer Science at the University of Trento. It provides a fundamental implementation of Particle Swarm Optimization (PSO) with support for cluster-based computations using OpenMPI, along with efficient thread parallelization through OpenMP.
Nov 22, 2022
Neural-PRNU-Extractor is a PyTorch-based project that extends FFDNet, originally designed for image denoising. It has been adapted to extract cameras' PRNU patterns. This project has been developed for the Signal, Image, and Video course within master's degree program in Artificial Intelligence Systems and Computer Science at the University of Trento.
Oct 1, 2022
DarkrAI is a project which consists in training two epsilon-greedy reinforcement learning agents for Pokémon battles. It has been developed for the University of Trento's Computer Science master's program as part of the Bio-Inspired Artificial Intelligence course.
Jul 29, 2022
Distributed Multi-level Cache is a distributed cache system with multiple levels designed to handle crashes at various hierarchy levels while ensuring client-centric consistency. This system was developed as part of the Distributed Systems 1 course in the Computer Science master's program at the University of Trento.
Apr 20, 2022
UDA is a collection of methods concerning unsupervised domain adaptation techniques, developed for the Deep Learning course of the Master's Degree program in Computer Science at the University of Trento.
Jul 20, 2021
This project represents my undergraduate thesis for a Computer Science degree at the University of Trento. It consists in developing an effective strategy for extracting the languages spoken by Wikipedia users, and extracting Wikipedia users’ user warnings and Wikibreaks, with a Focus on Studying their impact on users' activity level.
Apr 28, 2020
An efficient multithread and multiprocess program in C to analyze recursively the files contained inside a folder and produce statistics about them.
