I’m a third year PhD student at Politecnico di Milano advised by Prof. Matteo Matteucci.
My background is specifically into Signal Processing and Machine Learning. At the beginning of my studies I was mainly interested in audio signal processing, such as unsupervised techniques for blind source separation. Then, I surrendered to the charm of Deep Learning and during my MSc thesis I worked on a recurrent model for Semantic Segmentation.
My research currently focuses on Stability and Robustness of Deep Neural Networks (DNNs), in particular to adversarial attacks. Neural Networks are powerful models, but they are also particularly sensitive to imperceptible perturbations of the input. Much is still to be understood about their properties and this can be approached from different perspectives. I started analyzing robustness of DNNs from a dynamical system point of view, and I’m now digging also into Information Geometry and Optimization.
- Our paper “Attention Mechanisms for Object Recognition with Event-Based Cameras” has been accepted at WACV 2019!
- Our paper “NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations” has been accepted for poster presentation at NIPS conference 2018. See you in Montreal!
- I’ll be joining NVIDIA for a Summer Internship in Jan Kautz’s team from August 2018.
- I’ll be visiting Luigi Malagò’s group at RIST from May 2018 to July 2018.