What Happens After We Solve Continual Learning?

Join us for a talk by Stephanie Chan, Staff Research Scientist at DeepMind. This talk is part of the Kempner Seminar Series, a research-level seminar series that covers topics related to the basis of intelligence in natural and artificial systems.

Researchers often point to continual learning as a major missing component for modern AI models, and an area in which neuroscience may inform AI model development. With increased focus on this research area, we may soon find ourselves in a world with widely deployed continual learning agents. The benefits are endless, but continual learning also poses major challenges for AI safety and alignment — many existing techniques assume a single static base model (e.g. RLXF-based post-training), and are not suited for dynamically changing models. In this talk, I will lay out some challenges and examples. I will also describe potential starting points for technical solutions, drawing connections to catastrophic forgetting and to Quine’s “web of ideas”.

Stephanie Chan is a Staff Research Scientist at Google Deepmind. She received her PhD in computational neuroscience from Princeton University, and an SB in physics and an SB in brain & cognitive sciences, both from MIT. Her research covers a few broad areas. One set of work aims for a scientific understanding of modern AI models, especially in-context learning. She also works on developing AI systems for human enrichment and human empowerment. This has included work in AI for education, and AI to improve the information ecosystem. Now, her primary work revolves around understanding the future impacts of AI on society.