Towards Continual Learning on the Edge, Vincenzo Lomonaco - University of Bologna. Dipartimento di Informatica, Sala seminari ovest. Friday 14 February 2020, h 12.00 - Sala Seminari Ovest.

Abstract:

Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning, constantly and efficiently updating our biased understanding of the external world. On the contrary, current AI systems are usually trained offline on huge datasets and later deployed with frozen learning capabilities as they have been shown to suffer from catastrophic forgetting if trained continuously on changing data distributions. A common, practical solution to the problem is to re-train the underlying prediction model from scratch and re-deploy it as a new batch of data becomes available. However, this naive approach is incredibly wasteful in terms of memory and computation other than impossible to sustain over longer timescales and frequent updates. In this talk, we will introduce an efficient continual learning strategy, which can reduce the amount of computation and memory overhead of more than 45% w.r.t. the standard re-train & re-deploy approach, further exploring its real-world application in the context of continual object recognition, running on the edge on highly-constrained hardware platforms such as widely adopted smartphones devices."

Bio:

Vincenzo Lomonaco is a Postdoctoral Researcher at the University of Bologna, Italy and President of ContinualAI, a non-profit research organization and the largest open community on Continual Learning for AI. Currently, he is also a Co-founder and Board Member of AI for People and a Research Affiliate at AI Labs. Vincenzo obtained his PhD at UniBo in early 2019 with a dissertation titled "Continual Learning with Deep Architectures": a natural continuation of his master's thesis on neuroscience-inspired deep architectures he started in 2014. For more than 3 years he has been working as a teaching assistant for the “Machine Learning” and “Computer Architectures” courses in the Department of Computer Science of Engineering (DISI) in the same university. He has been a visiting research scientist at Purdue University, USA in 2017, at ENSTA ParisTech Grande École, France in 2018 and at Numenta, USA in 2019. His main research interests include open science and ethical AI developments, continual/lifelong learning with deep architectures, multi-task learning, knowledge distillation and transfer, and their applications to embedded systems, robotics and internet-of-things.