Tech Xplore on MSN

Mistaken correlations: Why it's critical to move beyond overly aggregated machine-learning metrics

MIT researchers have identified significant examples of machine-learning model failure when those models are applied to data ...
insideHPC

MIT: Machine Learning Models Too Judgmental on Rule Violations

CAMBRIDGE, Mass., May 10, 2023 — In an effort to improve fairness or reduce backlogs, machine learning models are sometimes designed to mimic human decision making, such as deciding whether social ...
Semiconductor Engineering

New Method Improves Machine Learning Models’ Reliability, With Less Computing Resources (MIT, U. of Florida, IBM Watson)

A new technical paper titled “Post-hoc Uncertainty Learning using a Dirichlet Meta-Model” was published (preprint) by researchers at MIT, University of Florida, and MIT-IBM Watson AI Lab (IBM Research ...