Groupe d’études et de recherche en analyse des décisions

Towards lifelong learning systems

Sarath Chandar Polytechnique Montréal, Canada

Sarath Chandar

Présentation sur YouTube

One of the grand challenges of Artificial Intelligence is to design artificial agents that can achieve human-level general intelligence. While deep learning has demonstrated super-human performance in several applications, current machine learning (ML) systems are highly specific to the task they were trained on and cannot generalize when faced with sequences of other tasks. Furthermore, even when faced with the original task, these systems cannot learn after deployment. Lifelong learning is a paradigm in ML where systems learn continuously over a sequence of tasks. Such systems, if realizable, can transfer knowledge between tasks, develop better priors for future tasks, and hence be as sample efficient as humans in learning. In this talk, I will discuss the core challenges in designing lifelong learning systems which include catastrophic forgetting and capacity saturation. Then, I will introduce new lifelong learning benchmarks which are inspired by realistic scenarios. Finally, I will explain the shortcomings of the existing replay-based algorithms for lifelong learning and introduce a new class of optimizers for lifelong learning. Our proposed optimizers are complementary to existing solutions and when combined with any of the existing solutions, result in even less catastrophic forgetting. Throughout the talk, I will also cover applications of lifelong learning in computer vision, natural language processing, and reinforcement learning. Towards the end, I will talk about the open questions in lifelong learning and promising future research directions.

Bio: Sarath Chandar is an Assistant Professor at Polytechnique Montreal where he leads the Chandar Research Lab. He is also a core faculty member at Mila, the Quebec AI Institute and holds a Canada CIFAR AI Chair. He received his PhD from the University of Montreal where he worked with Yoshua Bengio and Hugo Larochelle. His research interests include lifelong learning, deep learning, reinforcement learning, and natural language processing. He has served as a program committee member for ICML, NeurIPS, ICLR, and AAAI and as an area chair for ICLR 2021 and AAAI 2021. He has organized the Lifelong Learning workshop for the last four years. For more information about the speaker, please visit http://sarathchandar.in.