Bayesian Reasoning with Trained Neural Networks

We showed 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 were formulated as Bayesian inference problems, which we approximately solved through variational or sampling techniques. The approach built on top of already trained networks, and the addressable questions grew super-exponentially with the number of available networks. In its simplest form, the approach yielded conditional generative models. However, multiple simultaneous constraints constitute elaborate questions. We compared the approach to specifically trained generators, showed how to solve riddles, and demonstrated its compatibility with state-of-the-art architectures.

Automated summary

This study demonstrated the use of trained neural networks for Bayesian reasoning to solve tasks beyond their initial scope. Tasks were formulated as Bayesian inference problems, which were approximately solved through variational or sampling techniques, resulting in conditional generative models. The approach was shown to be compatible with state-of-the-art architectures and capable of solving complex multi-constraint problems.