IEEE

Addressing Data Distribution Shifts in Online Machine Learning Powered Smart City Applications Using Augmented Test-Time Adaptation

Abstract: Data distribution shift is a common problem in machine learning-powered smart city applications where the test data differs from the training data. Augmenting smart city applications with ...

Can you really be ‘fat but fit’? Here’s what the evidence says

Still, the findings reinforce what other research has suggested: thinness is not always protective, and extra weight is not ...
Datacenter Dynamics

Data centers come of age as critical infrastructure and good corporate citizens

No longer can data centers stand alone as isolated infrastructure, but are coming of age as critical supports for modern life and economies Around the world, nations are transforming into digital ...
WCTV

Something Good: Direct Auto Exchange hosts Thanksgiving drive-thru food distribution

TALLAHASSEE, Fla. (WCTV) - It’s time for Something Good and this one is a Thanksgiving Drive Thru. More good news: The event, sponsored by Direct Auto Exchange, was outside Havana’s City Hall ...
IEEE

On Data Distribution Leakage in Cross-Silo Federated Learning

Abstract: Federated learning (FL) has emerged as a promising privacy-preserving machine learning paradigm, enabling data owners to collaboratively train a joint model by sharing model parameters ...
The New York Times

After Shutdown, Labor Dept. Says Some Data Is Gone for Good

Surveys were delayed and some cannot be collected at all, officials said, further complicating the Federal Reserve’s decision on interest rates next month. By Lydia DePillis and Colby Smith The Bureau ...
The Conversation

When fake data is a good thing – how synthetic data trains AI to solve real problems

Ambuj Tewari receives funding from NSF and NIH. You’ve just finished a strenuous hike to the top of a mountain. You’re exhausted but elated. The view of the city below is gorgeous, and you want to ...