To discover new physics, AI may need to 'unlearn' the old one

A study in the Journal of Cosmology and Astroparticle Physics explores how a machine-learning strategy known as transfer learning could dramatically reduce the computational cost of searching for new physics beyond the standard cosmological model—while also revealing an unexpected risk: Sometimes AI systems can become too reliant on what they already know.

This report comes from Phys.org. The story centres on To discover new physics, AI may need to 'unlearn' the old one. Full coverage and background context is available at the original source. Readers seeking more detail on this developing topic are encouraged to follow updates from Phys.org and related outlets covering this beat.