Brubaker, MarcusYu, Jason Jiasheng2020-11-132020-11-132020-072020-11-13http://hdl.handle.net/10315/37900Normalizing flows are a class of probabilistic generative models which allow for fast density computation, efficient sampling, and are effective at modelling complex distributions like images. A drawback among current methods is their significant training cost, sometimes requiring months of GPU training time to achieve state-of-the-art results. This thesis introduces Wavelet Flow, a multi-scale, normalizing flow architecture based on wavelets. A Wavelet Flow has an explicit representation of signal scale that inherently includes models of lower resolution signals and conditional generation of higher resolution signals, i.e., super resolution. A major advantage of Wavelet Flow is the ability to construct generative models for high resolution data (e.g., 1024 1024 images) that are impractical with previous models. Furthermore, Wavelet Flow is competitive with previous normalizing flows in terms of bits per dimension on standard (low resolution) benchmarks while being up to 15 faster to train.Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.Artificial intelligenceElectronic Thesis or Dissertation2020-11-13ComputerVisionComputer visionArtificial intelligenceWaveletsHaarNormalizing flowInvertible neural networksNeural networksDeep learningGenerative modellingDensity estimationMulti-scaleImage generation