ASCL.net

Astrophysics Source Code Library

Making codes discoverable since 1999

ASCL Code Record

[ascl:2307.061] connect: COsmological Neural Network Emulator of CLASS using TensorFlow

connect (COsmological Neural Network Emulator of CLASS using TensorFlow) emulates cosmological parameters using neural networks. This includes both sampling of training data and training of the actual networks using the TensorFlow library. connect aids in cosmological parameter inference by immensely speeding up the process, which is achieved by substituting the cosmological Einstein-Boltzmann solver codes, needed for every evaluation of the likelihood, with a neural network with a 102 to 103 times faster evaluation time. The code requires CLASS (ascl:1106.020) and Monte Python (ascl:1307.002) if iterative sampling is used.

Code site:
https://github.com/AarhusCosmology/connect_public
Described in:
https://ui.adsabs.harvard.edu/abs/2023JCAP...05..025N
Bibcode:
2023ascl.soft07061N

Views: 1054

ascl:2307.061
Add this shield to your page
Copy the above HTML to add this shield to your code's website.