Sunday, January 31, 2021

'Liquid' machine-learning system adapts to changing conditions

Researchers developed a neural network that learns on the job, not just during training. The 'liquid' network varies its equations' parameters, enhancing its ability to analyze time series data. The advance could boost autonomous driving, medical diagnosis, and more.

from Latest Science News -- ScienceDaily https://ift.tt/3cowxN7
at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Two monster black holes just collided — it’s so massive, it shouldn’t exist

Two colossal black holes—among the most massive ever seen—collided in deep space, creating gravitational waves that rippled across the cosmo...