Continual Learning (CL) studies the problem of learning from a stream of data from changing domains, each connected to a different learning task. The objective of CL is to quickly adapt to new situations or tasks by exploiting previously acquired knowledge while protecting previous learning from being erased. Meeting the objectives of CL will provide an opportunity for systems to quickly learn new skills given knowledge accumulated in the past and continually extend their capabilities to changing environments, a hallmark of natural intelligence. CL has been a growing field of interest in the Machine Learning community over the past few years. However, researchers are yet to converge on the same desiderata for this problem. Furthermore, experimental setups are often more distant from real applications than other fields. We will welcome submissions on all aspects of continual learning. In particular, the focus of our workshop will be to help identify the applications of, evaluation of, and methodology for CL. Furthermore, we are also interested in submissions that draw connections to other areas, such as Neuroscience, Bayesian Learning, Reinforcement Learning, and Meta-learning.

Code of conduct

All attendees must comply with the ICML 2020 code of conduct. We empower and encourage you to report any behavior that makes you or others feel uncomfortable by contacting the ICML Diversity and Inclusion co-chairs.

The workshop organizers are committed to promote a culture of diversity, inclusion, respect, and acceptance on all levels. The organizing committee and invited speakers reflect our commitment to diversity in different perspectives on CL, seniority, gender, race, backgrounds, and affiliations.