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.
Source
Phys.org
Opens original article in a new tab

