Abstract: | Autoregressive models parametrized as deep neural networks (called PixelCNN) achieve state-of-the-art results in image density estimation. Although training is fast, sampling is costly, requiring one network evaluation per pixel; O(N) for N pixels. In this talk, I will describe a parallelized PixelCNN that achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of high-resolution images. Results will be presented on class-conditional image generation, text-to-image synthesis, and action-conditional video generation. In the second part of the talk, I will discuss density estimation in the low-data regime as a meta learning problem. Scott is a research scientist at DeepMind. He completed his PhD with Honglak Lee at the University of Michigan in 2016. His research focuses on deep learning methods for image generation, object detection, imitation learning and program induction. |