🎓Education

In this section you will find an overview of my education.

PhD in Information Engineering at the University of Pisa

Nov 2021 - Present (Pisa, PI)

Summer School on Large-Scale AI for Research and Industry

Sep 2023 (Modena, MO)

This Summer School has been organized by the European Lab for Learning and Intelligent Systems in collaboration with NVidia, UNIMORE and CINECA. I have been selected for participation and I attended several days of lessons taken by experts in large-scale AI working at Google, Deepmind, Meta, Huggingface, NVidia and Cineca. The main focus of these talks was on large-scale AI and how to train large models effectively. During the school I also worked on a Deep Learning project on per-object distance estimation. To conduct the experiments, my team had access to and worked on the LEONARDO cluster, the fourth supercomputer worldwide, receiving also training on how to use it from experts by NVidia and CINECA.

Master's Degree in Artificial Intelligence and Data Engineering at the University of Pisa

Sep 2019 - Jul 2021 (Pisa, PI)

Thesis: Design and Development of Transformer-based methods for Video Deepfake Detection. The main contribution of this thesis is the application of this architecture and the development of other alternative architectures based on Vision Transformers and EfficientNet for the detection of deepfakes and to the more general task of anomaly detection. The problem of the identification of anomalous situations in videos of surveillance cameras is tackled, and a comparison between various architectures and versions of the transformers is given, studying their effectiveness in this context, which has never been faced before through the use of this innovative deep learning method. Second, experiments are conducted on the deepfake detection task developing several hybrid architectures of Vision Transformers and convolutional networks, achieving near state-of-the-art performance with networks trained from scratch and partially based on fine-tuning of pretrained networks.

Bachelor's Degree in Computer Engineering at the University of Pisa

Sep 2014 - Feb 2019 (Pisa, PI)

Thesis: Analysis of the perception of chromatic differences as the resolution changes using an artificial neural network. Identifying the perceptive differences between two images is a big problem of the colourimetry industry. I discovered that they could do that using low resolutions images, getting better results with lower cost and time waste.