Developed by the NCI Training Team, this course showcases how neural networks rapidly emulate summary statistics from astronomy models.
Are you a Bayes fan but your amazing model is just not up to the task because with great power comes great computing power (consumption) as well? Look no further, in this course, we will showcase how one can easily construct a neural network to rapidly emulate summary statistics from (almost) any complex models. We will also demonstrate how to write a simple Bayesian framework to perform inference with the emulator.
NCI is developing a series of AI/ML course with experts from various disciplines. This training is designed to be the first course for astronomers. As such, it aims to help attendees
- raise awareness of different applications of AI/ML in astronomy,
- construct a neural network to emulate a complex model,
- build a simple framework to perform Bayesian inference.
- Models in astronomy (CMB, 21-cm, IGM neural fraction, Galaxy population)
- AI/ML in astronomy
- Basics of neural network
- activation function
- types of neural networks
- training neutral networks
- Data preparation (using the recent 21-cm inference work as demonstration, https://arxiv.org/abs/2108.07282)
- Write and train a neural network step by step
- Write and perform a Bayesian framework step by step