Assistant Professor,
Computer Science
Sunday, April 28, 2024, 15:00
- 16:30
Building 9, Level 2, Room 2325
Contact Person
Most existing AI learning methods can be categorized into supervised, semi-supervised, and unsupervised methods. These approaches rely on defining empirical risks or losses on the provided labeled and/or unlabeled data. Beyond extracting learning signals from labeled/unlabeled training data, in this talk, I will cover a class of methods that I have been developing for over a decade, which can learn beyond the vocabulary that was trained on and can compose or create novel concepts.