[ContinualAI Reading Group] EEC: Learning to Encode and Regenerate Images for Continual Learning

This Friday 19-02-2021, 5.30pm CET , for the ContinualAI Reading Group, Ali Ayub (Pennsylvania State University) will present the paper:

Title: EEC: Learning to Encode and Regenerate Images for Continual Learning

Abstract: The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains autoencoders with Neural Style Transfer to encode and store images. During training on a new task, reconstructed images from encoded episodes are replayed in order to avoid catastrophic forgetting. The loss function for the reconstructed images is weighted to reduce its effect during classifier training to cope with image degradation. When the system runs out of memory the encoded episodes are converted into centroids and covariance matrices, which are used to generate pseudo-images during classifier training, keeping classifier performance stable while using less memory. Our approach increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.

The event will be moderated by: Vincenzo Lomonaco .

:pushpin: Eventbrite event: EEC: Learning to Encode and Regenerate Images for Continual Learning Tickets, Fri, Feb 19, 2021 at 5:30 PM | Eventbrite
:pushpin: Miscrosoft Teams: click here to join