About

I am a third-year Ph.D. student in Information Engineering at the University of Padova, part of the SIGNET research group, and supervised by Professor Michele Rossi. I hold a Bachelor’s degree in Mathematics and a Master’s in Data Science. My main research interest is in the field of Neuromorphic Engineering, with a focus on the development of gradient-free training strategies for Spiking Neural Networks (SNNs).

At SIGNET, my research spanned across various domains. Initially, I focused on developing deep learning architectures for human mmWave radar sensing, specifically addressing Open-Set gait recognition from mmWave point cloud traces. Over time, my interests have expanded towards energy-efficient deep learning techniques for edge computing, with projects involving Joint Communication and Sensing, federated learning, and spike encoding for Spiking Neural Networks (SNNs).

Currently, my primary research interests are focused on foundational methodological aspects of SNNs, particularly in exploring gradient-free training methods. I have dedicated a significant portion of my PhD to studying the foundational literature in computational neuroscience. I have explored the usage of Spike Timing Dependent Plasticity (STDP) and Reward-modulated STDP for local training of SNNs. My goal is to contribute to bridging the existing gaps the fields of neuroscience and machine learning, enabling the development of new computational models inspired by the brain’s mechanisms.

Currently, I am working on applying mathematical optimization techniques for the training of SNN models.

Previous Research Activity

I first approached machine learning during my Bachelor’s thesis, where I worked on a data-driven approach for the prediction of severe malaria cases, in a joint collaboration with Ospedale Lazzaro Spallanzani in Rome, supervised by Professor Francesco Rinaldi. Our work was later published as a journal paper.

For my Master’s thesis, I had the opportunity to work on Neural Symbolic Integration under the guidance of Professor Luciano Serafini and researcher Alessandro Daniele at Fondazione Bruno Kessler in Trento. Specifically I carried out the experimental section of “Knowledge Enhanced Neural Networks” (KENN).