ECoPANN

ECoPANN (Estimating Cosmological Parameters with Artificial Neural Network)

ECoPANN is a new method to estimate cosmological parameters accurately based on ANN. It is an alternative to the traditional Markov chain Monte Carlo (MCMC) method, and can obtain almost the same results as MCMC.

ECoPANN can be applied to the research of cosmology and even other broader scientific fields.

It is proposed by Guo-Jian Wang, Si-Yao Li, Jun-Qing Xia (2020).

Documentation

The documentation can be found at ecopann.readthedocs.io.

Attribution

If you use this code in your research, please cite Guo-Jian Wang, Si-Yao Li, Jun-Qing Xia, ApJS, 249, 25 (2020).

Dependencies

The main dependencies of ecopann are:

• PyTorch
• CUDA (optional, but suggested)
• coplot

and some commonly used modules:

• os
• sys
• numpy
• scipy
• math
• decimal
• matplotlib
• smt
• logging
• warnings
• time

Installation

You can install ecopann by using pip:

$ sudo pip install ecopann

or from source:

$ git clone https://github.com/Guo-Jian-Wang/ecopann.git
$ cd ecopann
$ sudo python setup.py install

License

Copyright 2020-2020 Guojian Wang

ecopann is free software made available under the MIT License. For details see the LICENSE file.