Robustness, structure and hierarchy in deep generative models

Thesis

Deep learning provides us with ever-more-sophisticated neural networks that can be tuned via gradient ascent to maximise some objective. Bayesian statistics provides us with a principled and unified approach to specify statistical models and to perform inference. One productive way to pair these two methodologies results in Deep Generative Models (DGMs), where the mappings between the statistical parameters in a probabilistic model are themselves parameterised using neural networks. In thi...

Expand abstract

Authors: Willetts, MJF

• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: Englinsh
• Keywords: deep generative models; variational autoencoders; adversarial attacks; latent variable models
• Subjects: Deep learning (Machine learning); Machine learning; Statistics