( events)   Timezone: »  
Fri Dec 13 08:00 AM -- 06:00 PM (PST) @ West Ballroom B
Roberto Calandra · Ignasi Clavera Gilaberte · Frank Hutter · Joaquin Vanschoren · Jane Wang

Workshop Home Page

Recent years have seen rapid progress in meta­learning methods, which learn (and optimize) the performance of learning methods based on data, generate new learning methods from scratch, and learn to transfer knowledge across tasks and domains. Meta­learning can be seen as the logical conclusion of the arc that machine learning has undergone in the last decade, from learning classifiers, to learning representations, and finally to learning algorithms that themselves acquire representations and classifiers. The ability to improve one’s own learning capabilities through experience can also be viewed as a hallmark of intelligent beings, and there are strong connections with work on human learning in neuroscience. The goal of this workshop is to bring together researchers from all the different communities and topics that fall under the umbrella of meta­learning. We expect that the presence of these different communities will result in a fruitful exchange of ideas and stimulate an open discussion about the current challenges in meta­learning, as well as possible solutions.

Opening Remarks
Meta-learning as hierarchical modeling (Talk)
How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction (Talk)
Poster Spotlights 1 (Spotlight)
Coffee/Poster session 1 (Poster Session)
Interaction of Model-based RL and Meta-RL (Talk)
Discussion 1 (Discussion Panel)
Abstraction & Meta-Reinforcement Learning (Talk)
Scalable Meta-Learning (Talk)
Poster Spotlights 2 (Spotlight)
Coffee/Poster session 2 (Poster Session)
Contributed Talk 1: Meta-Learning with Warped Gradient Descent (Sebastian Flennerhag) (Talk)
Contributed Talk 2: MetaPix: Few-shot video retargeting (Jessica Lee) (Talk)
Compositional generalization in minds and machines (Talk)
Discussion 2 (Discussion Panel)