Presenter: Jakob Knollmüller, ORIGINS Data Science Lab/TUM
Title: Bayesian Reasoning with Trained Neural Networks
Abstract: We show how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope. Deep generative models provide prior knowledge, and classification/regression networks impose constraints. The tasks at hand are formulated as Bayesian inference problems, which we approximately solve through variational or sampling techniques. The approach builds on top of already trained networks, and the addressable questions grow super-exponentially with the number of available networks. In its simplest form, the approach yields conditional generative models. However, multiple simultaneous constraints constitute elaborate questions. We compare the approach to specifically trained generators, show how to solve riddles, and demonstrate its compatibility with state-of-the-art architectures.
As usual, the format will be a short presentation followed by plenty of discussion.
Please let all interested know about the Journal Club (get them to send their Email address). We are looking forward to lively discussions.