home All News open_in_new Full Article

Novel 'pruning' technique shows promise for reducing AI bias without harming performance

A method known as "model pruning" can be used to pinpoint and remove neurons that consistently contribute to biased responses, say researchers at the Stanford Law School and the Stanford Institute for Human-Centered AI.


today 40 h. ago attach_file Politics

attach_file Events
attach_file Politics
attach_file Politics
attach_file Economics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Events
attach_file Politics
attach_file Politics
attach_file Politics
attach_file Events
attach_file Events
attach_file Technology
attach_file Politics


ID: 2683806531
Add Watch Country

arrow_drop_down