example cover photo

Welcome to my webpage!

I'm a computer scientist based in Ferrara, Italy

About

I'm an Italian computer scientist specialized in Machine Learning.
I've studied in Gothenburg , Singapore , and Sydney , and I'm now based in Ferrara .
I love tackling hard tasks with AI, analyzing data, running machine learning sessions and implementing innovative ideas.
My goal for 2025 and 2026 is to deploy my technical skills for AI-based entrepreneurial ideas.
Please get in touch if you want to chat! 💬

Here are my resume & email:

(English)
(Italian)
giovanni.pagliarini☀️aol.com

Why AI?

Doing stuff can be entertaining... or not. But automating stuff is quite likely to be entertaining! 🗿 Automating something forces you to understand it deeply, which is a great exercise for the mind! Best part is, if you manage to automate something that was not entertaining to do in the first place, you can then choose to never do that thing again, and spend your time with your loved ones instead 😁! Artificial Intelligence (AI) is the essence of automating hard tasks. A hard task is one that you as a human can carry out, but have trouble teaching a digital computer to perform, perhaps because there is no “perfect” procedure for it, or because the thought process required for solving it is complex and unclear, even to you. Machine Learning, today's primary enabler of AI, seeks the solution in data. Data has the answers to many hard questions... You just have to word your questions in the right way.

Research

At ACLAI Lab (University of Ferrara) I have designed symbolic machine learning algorithms and initiated the Sole.jl framework for symbolic AI. My main research line has revolved around the idea of equipping standard decision trees with the ability of performing temporal or spatial reasoning, so that they can natively handle time series, images, videos and, more generally, unstructured data that extends along temporal and/or spatial dimensions. We have adopted tractable logical formalisms that are able to express entity-relation reasoning, such as predicate logics or modal logics of space and time. The team I work with is a mixture of logicians interested in modal logic, and machine learning people interested in interpretability; we have been following this lead for about four years, achieving remarkable results on a few tasks of time series classification and image classification. Check out my publications.