AI Seminar Series 2023: Anna Koop

The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.

On September 11, Anna Koop —a Research Engineer at Google DeepMind — presented “Experiential Learning with Partition-Tree Weighting and MAML" at the AI Seminar.

Abstract:
Learning from experience means remaining adaptive and responsive to errors over time. However, gradient-based deep learning can fail dramatically in the continual, online setting.

In this presentation, Koop addresses this shortcoming by combining two meta-learning methods: the purely online Partition Tree Weighting (PTW) mixture-of-experts algorithm, and a novel variant of the Model-Agnostic Meta-Learning (MAML) initialization-learning procedure. She demonstrates the approach, Replay-MAML PTW, in a piecewise stationary classification task. In this continual, online setting, Replay-MAML PTW matches and even outperforms an augmented learner that is allowed to pre-train offline and is given explicit notification when the task changes. Replay-MAML PTW thus provides a base learner with the benefits of offline training, explicit task sampling, and boundary notification, all for a O(log2 (t)) increase in computation and memory. This makes deep learning more viable for fully online, task-agnostic continual learning, which is at the heart of general intelligence.

Watch the full presentation below:

Want to learn how you can kick-start your AI career? Find out more about Amii's Career Accelerator to find out more.