Efficient technique improves machine-learning models' reliab

A new technique can enable a machine-learning model to quantify how confident it is in its predictions, but does not require vast troves of new data and is much less computationally intensive than other techniques. The work was led by researchers from MIT and the MIT-IBM Watson AI Lab.

Related Keywords

Soumya Ghosh , Gregory Wornell , Maohao Shen , Prasanna Sattigeri , Subhro Das , Watson Ai Lab , Research Laboratory Of Electronics , University Of Florida , Algorithms Laboratory , Us National Science Foundation , Research Laboratory , Sumitomo Professor , Machine Learning , Explainable Ai , Uncertainty Quantification , Peta Model ,