Improved supervised learning methods for EoR parameters reconstruction

no code implementations • 8 Apr 2019 • Aristide Doussot, Evan Eames, Benoit Semelin

When using an un-noised signal as input, we improve on previous neural network accuracy by one order of magnitude and, using local ridge kernel regression, we gain another factor of a few.

Cosmology and Nongalactic Astrophysics

Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks

no code implementations • 24 Jan 2017 • Hayato Shimabukuro, Benoit Semelin

Then we test the trained network on the new set of 54 test samples with different values of the parameters.

Cosmology and Nongalactic Astrophysics