Learning to learn and compositionality with deep recurrent neural networks

Author: Nando de Freitas, Department of Computer Science, University of Oxford Abstract: Deep neural network representations play an important role in computer vision, speech, computational linguistics, robotics, reinforcement learning and many other datarich domains. In this talk I will show that learningtolearn and compositionality are key ingredients for dealing with knowledge transfer so as to solve a wide range of tasks, for dealing with smalldata regimes, and for continual learning. I will dem