Abstract: Significant amount of machine learning applications on astrophysical data have hinted at remarkable versatility and vast potential of artificial intelligence (AI) in the era of exascale computation and data-driven modeling. However, cosmological studies often pose unique challenges due to the observational nature of the field, and require novel developments in AI-based methodologies.

A subset of these crucial issues will be discussed in this talk, with emphasis on the adaptation of numerical simulations and synthetic data, interpretabilit, and explainability, uncertainty quantification, and scalability. Bayesian inference of cosmological parameters, redshift estimation of galaxies, strong lensing studies, and other key topics at the intersection of computation cosmology and scientific machine learning will be explored.