Federated learning was devised to solve the problem of difficulty in aggregating personal data, such as patient medical records or financial data, in one place. However, during the process where each institution optimizes the collaboratively trained AI to suit its own environment, a limitation arose: The AI became overly adapted to the specific institution’s data, making it vulnerable to new data.
Federated learning AI developed for hospitals and banks without personal information sharing
Reader’s Picks
-
Life satisfaction among spouses aged over 50 is strongly interrelated, according to a longitudinal study by the University of Eastern [...]
-
Why do some people endorse claims that can easily be disproved? It’s one thing to believe false information, but another [...]
-
Grandparents can play a critical role in helping mediate their grandchildren’s media use and serve as an ally for their [...]