English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Bayesian reasoning with trained neural networks

MPS-Authors
/persons/resource/persons212631

Knollmüller,  Jakob
Computational Structure Formation, MPI for Astrophysics, Max Planck Society;

/persons/resource/persons16142

Ensslin,  Torsten A.
Computational Structure Formation, MPI for Astrophysics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Knollmüller, J., & Ensslin, T. A. (2021). Bayesian reasoning with trained neural networks. Entropy, 23(6): 693. doi:10.3390/e23060693.


Cite as: https://hdl.handle.net/21.11116/0000-0009-5925-A
Abstract
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.