Vittorio Mazzia - About Me

I'm a research scientist at Amazon AGI. Previously, at Politecnico di Torino as a Ph.D. student, working in synergy with the two interdepartmental centers, PIC4SeR and SmartData.

I spent my Ph.D. years researching novel deep learning algorithms for enhanced artificial perception, autonomous navigation, path planning, and sensorimotor solutions for service robotics. Furthermore, I worked on the efficiency of machine learning algorithms for embedded AI at the edge, using neural compute devices for hardware acceleration.

My current research focuses on delving into the capacities and limitations of large neural models. Specifically, I am intrigued by the intricate process through which sensory signals contribute to shaping a comprehensive model of the world, and the potential role this model can play in mitigating existing limitations within large-scale models. Always, neural efficiency and generalization are my driving principles.