A more effective way to train machines for uncertain, real-world situations
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
Selecting the right method gives users a more accurate picture of how their model is behaving, so they are better equipped to correctly interpret its predictions.
The machine-learning algorithm identified a compound that kills Acinetobacter baumannii, a bacterium that lurks in many hospital settings.
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.
A new machine-learning model makes more accurate predictions about ocean currents, which could help with tracking plastic pollution and oil spills, and aid in search and rescue.
Models trained using common data-collection techniques judge rule violations more harshly than humans would, researchers report.
Citadel founder and CEO Ken Griffin visits MIT, discusses how technology will continue to transform trading and investing.
Matt Shoulders will lead an interdisciplinary team to improve RuBisCO — the photosynthesis enzyme thought to be the holy grail for improving agricultural yield.
A new computer vision system turns any shiny object into a camera of sorts, enabling an observer to see around corners or beyond obstructions.