Speaker
Description
In this talk, I will show applications of the state-of-the-art supervised, un-supervised and weakly-supervised machine learning (ML) algorithms to solve problems in cosmology and astronomy. I will show ML-based galaxy clusters' mass modeling to capture the Sunyaev Zel'dovich (SZE) and Cosmic Microwave Background (CMB) lensing effects, using convolutional neural networks (CNNs). I will show an application of self-organizing maps (SOMs) to discover new radio sources in the Australian Square Kilometre Pathfinder surveys (ASKAP). I will also present state-of-the-art weakly supervised ML methods to classify and segment radio galaxies on cosmological scales. All these methods are domain agnostic and can be easily applied to other fields of physics.
| Session | Astroparticle Physics and Cosmology |
|---|
