Specialization of deep learning architectures for modeling brain activity and function

The course is part of the PhD programme in "Health and Technology" and will be held by Prof. Nicola Toschi, Associate Professor in Medical Physics at the University of Rome Tor Vergata.

  • Date: 14 MARCH 2022  from 14:30 to 17:30

  • Event location: Room 1.3 - School of Engineering - Viale Risorgimento, 2 - Bologna - Online event

  • Type: Seminar


In the last 5 years, the advent of deep learning (DL) paradigms has revolutionized the field of artificial intelligence (AI). Previously, the contribution of AI across disciplines was confined to applications whose overall complexity is low, and towered by that of human physiology. However, modern DL paradigms offer unprecedented ability to integrate multimodal, multi-domain, and multiscale data with previously unimaginable prediction performance and little or no need for data preprocessing. With advent of ‘big’, publicly available, and often multidomain data repositories it is now possible to build and validate AI frameworks with a tangible potential to boost neuroscience research, enhance decision-making in disease management algorithm, and enrich next-generation clinical trials. This seminar will focus on the latest developments and deep architectures for modeling and studying biomedical data in general and brain structure and function in particular, as measured through e.g. MEG, EEG, or MRI. Particular emphasis will be given to key architectural developments like e.g. separable convolutions, multi-head attention networks, spiking neural networks graph and contrastive learning. Every example will include a use-case stemming from an ongoing or published study.




Nicola Toschi is an Associate Professor in Medical Physics at the university of Rome Tor Vergata and Research Staff and Associate Investigator at the A.A. Martinos Center for Biomedical Imaging - Harvard Medical School/MGH. He has an interdisciplinary background in physics, mathematics and neuroscience. His research is focused on the development of mechanistic, statistical and intelligent models for understanding physiological phenomena, advanced image generation and processing, modelling of neuronal activity, nanoparticle physics and bioactivity, and the development of software/hardware interfaces for real-time biomedical data acquisition He also has a strong focus on MR physics and ultra-high field human MR imaging, and regularly serves as a senior biostatistician, machine learning and parallel computing consultant in fundamental biological/biomarker research (genetic, epigenetic, imaging) as well as an image acquisition and processing. He is the author or co-author of approximately 250 peer-reviewed publications in these fields, which have been cited around 5500 times since year 2000.


Stefano Diciotti

Associate Professor

Write an e-mail

Go to the website