webinar register page

Webinar banner
Continual Learning for Natural Language Processing Tasks
Abstract: The classic machine learning paradigm learns in isolation, which is only suitable for well-defined narrow tasks in closed environments. It is far from sufficient for truly intelligent systems, which must learn continually, accumulate the knowledge learned in the past, and selectively transfer the knowledge to help learn each new task. The machine learning paradigm, continual/lifelong learning, aims to achieve these goals. In this talk, I will first introduce the context of and motivation for continual learning and then discuss some of our recent work on continual learning of natural language processing tasks.

Sep 22, 2021 05:30 PM in Tehran

Webinar is over, you cannot register now. If you have any questions, please contact Webinar host: Online Conference.