Model-Agnostic Meta-Learning: Universality, Inductive Bias, and Weak Supervision

Meta-learning holds the promise of enabling machine learning systems to replace manual engineering of hyperparameters and architectures, effectively reuse data across tasks, and quickly adapt to unexpected scenarios. In this talk, I will present a unified view of the meta-learning problem, discussing how a variety of approaches attempt to solve the problem, and when we might prefer some approaches over others. Further, I will discuss interesting theoretical and empirical properties of the model-agnostic meta-learning algorithm. Finally, I will conclude by showing new results on learning to learn from weak supervision with applications in imitation learning on a real robot and human-like concept acquisition.