Pixel Recurrent Neural Networks | Seminar final v1

As part of the course “LINFO2369 - Machine Learning and Artifical Intelligence Seminar“ we were asked to produce a video explaining a paper of our choice. “Pixel Recurrent Neural Networks“; Aaron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu “Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an effective use of residual connections in deep recurrent networks. We achieve log-likelihood scores on natural images that are considerably better than the previous state of the art. Our main results also provide benchmarks on the diverse ImageNet dataset. Samples generated from