Hybrid Physical-Deep Learning Model for Astronomical Inverse Problems [article]

Francois Lanusse, Peter Melchior, Fred Moolekamp
2019 arXiv   pre-print
We present a Bayesian machine learning architecture that combines a physically motivated parametrization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals. This combination yields an interpretable and differentiable generative model, allows the incorporation of prior knowledge, and can be utilized for observations with different data quality without having to retrain the deep network. We demonstrate our
more » ... with an example of astronomical source separation in current imaging data, yielding a physical and interpretable model of astronomical scenes.
arXiv:1912.03980v1 fatcat:rtqnopmnangflntdawsrqseuuy