MIT: Researchers Reduce Bias in AI Models While Preserving or Improving Accuracy
December 12, 2024
December 12, 2024
CAMBRIDGE, Massachusetts, Dec. 12 (TNSres) -- The Massachusetts Institute of Technology issued the following news:
* * *
A new technique identifies and removes the training examples that contribute most to a machine-learning model's failures.
* * *
By Adam Zewe, MIT News
Machine-learning models can fail when they try to make predictions for individuals who were underrepresented in the datasets they were trained on.
* * *
A new technique identifies and removes the training examples that contribute most to a machine-learning model's failures.
* * *
By Adam Zewe, MIT News
Machine-learning models can fail when they try to make predictions for individuals who were underrepresented in the datasets they were trained on.