ReSt - A Deep Learning Approach for Italian Stereotype Detection in Social Media
Description: The Hate Speech Detection (HaSpeeDe 2) task presented at Evalita 2020 was composed of the main task (hate speech detection) and two Pilot tasks (stereotype and nominal utterance detection). This project aims to investigate different models for solving the stereotype detection task. This project was developed for the course of Human Language Technologies at the University of Pisa under the guide of Prof. Giuseppe Attardi.
Computational Mathematics for Learning and Data Analysis
Description: The aims were to extend ISANet lib in order to include the NCG FR/PR/HS and beta+ variants, and the L-BFGS methods (as new optimizers) and study the objective function used during the learning phase from a mathematical and optimisation point of view. Developed during the Computational Mathematics for learning and data analysis course held by Prof. Antonio Frangioni and Prof. Federico Poloni.
Machine Learning ProjectPython
Description: The aims were to implement a Machine Learning (ML) model simulator, to understand the effect of hyper-parameters and to solve a supervised regression learning task. Developed during the ML course held by Prof. Alessio Micheli at the University of Pisa.
ISANet - Neural Network Library
Description: ISANet library provides a flexible and modular neural network library. It was entirely developed in Python using Numpy as a package for scientific computation and it is the result of the machine learning course held by Professor Alessio Micheli at Department of Computer Science of University of Pisa. ISANet is composed of low (Keras-like) and high-level (Scikit-learn-like) APIs divided into modules.
Data Mining Project
Description: Carvana is a start-up business launched by a well-established American company. The goal is to change completely the way people buy, finance, and trade their used vehicles by replacing physical infrastructure with technology and top of the line scientific models. This project shows the analysis based on the dataset published on kaggle.com for the Data Mining 2019/2020 Project. The aim is to build a model to advise future customers whether a purchase could be a good or bad buy.
ISA - ChatterBot
Description: ISA is a Rule-Based system ChatterBot AI written in Prolog derived from Weizenbaum’s original Eliza program. This ChatterBot was born from the idea of developing an artificial intelligence expert in advising films and TV shows.
Console Messages Application
Description: ”messaging” system written in C, that allows the exchange of messages between different users (clients), communication takes place directly (P2P) or via exchange of offline messages (Client-Server). Uses: signal handling, pthread library, socket library (tcp, udp socket), Model–View–Controller (usually known as MVC) has been used as architectural pattern.
HTML, CSS AND JS
Description: My personal website hosted using Github pages, with a landing page, blog, list projects and a resume pages.
Pseudorandom Numbers and White Noise Generation
Description: Generate a white noise. Each sample of white noise is a uniformly random value in the range of [-1.0 .. 1.0). Uses: portaudio (cross-platform, open-source, audio I/O library) as audio backend, signal handling and Pthread library.
System Administrator Project
ESXI, DEBIAN, HP SERVER
Description: Deployed a HP server with VMWARE ESXI 6.7 and multiple VPS( Virtual Private Server)