[ContinualAI Reading Group] Energy-Based Models for Continual Learning

This Friday 18-12-2020 at 11.30 am ET, for the ContinualAI Reading Group, Shuang Li (MIT) will present the paper:

Title: "Energy-Based Models for Continual Learning"

Abstract: We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs have a natural way to support a dynamically-growing number of tasks or classes that causes less interference with previously learned information. We find that EBMs outperform the baseline methods by a large margin on several continual learning benchmarks. We also show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. These observations point towards EBMs as a class of models naturally inclined towards the continual learning regime.

The event will be moderated by: Vincenzo Lomonaco.

:round_pushpin:Eventbrite Event (to save it on your calendar): https://www.eventbrite.it/e/energy-based-models-for-continual-learning-tickets-132785574227
:round_pushpin:Miscrosoft Teams link: click here to join