Bayesian Reasoning with Trained Neural Networks
This work addresses the challenge of extending the utility of pre-trained neural networks for broader inference tasks, though it appears incremental as it builds on existing networks and techniques.
The paper tackled the problem of enabling trained neural networks to perform Bayesian reasoning for tasks beyond their original scope, using deep generative models as priors and classification/regression networks as constraints, and demonstrated its application in solving riddles and compatibility with state-of-the-art architectures.
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.