Matteo Tiezzi

I am a post-doctoral researcher in the Siena Artificial Intelligence Laboratory, tutored by Prof. Stefano Melacci. I obtained my PhD at the University of Siena, Italy, defending a thesis entitled “Local Propagation in Neural Network Learning by Architectural Constraints”, supervised by Prof. Marco Maggini.

I am generally interested in Artificial Intelligence and other connected areas of computer science. My recent contributes are related to both the application of Deep Learning models to computer vision and video analysis, and fundational studies regarding novel learning algorithms and neural models. I am particularly interested in the emerging field of non-euclidean Deep Learning, in particular in Graph Neural Networks.

Education

I received my B.S in Computer and Information Engineering at Siena, with a thesis titled “Automatic Extraction of relevant information from Web Pages, using XPath“.
In 2017 I completed my M.S. in Computer and Automation Engineering at Siena, summa cum laude.
My thesis was titled “Traffic event monitoring using Recurrent Neural Networks“.

PhD Thesis

In March 2021 I defended my PhD Thesis entitled “Local Propagation in Neural Network Learning by Architectural Constraints”.

Projects

:: GNN Framework
We provide an implementation of the Graph Neural network model, developed under the supervision of the authors of the original work.
You can find a description of the model, installation/usage tutorials and some examples in the Gnn site.
We provide a github repo containing our implementation and a pip package to easily install our software.

:: Learning in Visual Environment
This project aim at developing intelligent agents with visual skills that operate in a given environment.

:: Vulgaris
Analysis of Italian Diachronic Language Varieties.

:: SAILenv: Learning in Virtual Visual Environments Made Simple
SAILenv is a platform that makes it easy to customize and interface 3D Virtual Environments with your Machine Learning algorithms. It is powered by Unity, and it is capable of generating frames at real-time speed, providing full pixel-wise annotations (semantic and instance labeling, depth, optical flow). It includes 3+1 pre-built scenes.
SAILenv comes with a Python API, designed to easily integrate with the most common learning frameworks.

Awards

:: 1st place Hackathon Soccer Data Challenge.
Predicting football players modern roles and analysis of teams’s best schemes.

Publications

You can find my articles on my Google Scholar profile and Researchgate profile.

GitHub and Personal Web page

You can find some software I mantain in my GitHub.
Have a look at my personal page, where you can find my CV, other publications and my talks.

Contacts

You can email me at     mtiezzi at diism dot unisi dot it, or through my Linkedin.