A simpler method for learning to control a robot
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
A faster way to teach a robot
A new technique helps a nontechnical user understand why a robot failed, and then fine-tune it with minimal effort to perform a task effectively.
A new way to look at data privacy
Researchers create a privacy technique that protects sensitive data while maintaining a machine-learning model’s performance.
Learning the language of molecules to predict their properties
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
Researchers teach an AI to write better chart captions
A new dataset can help scientists develop automatic systems that generate richer, more descriptive captions for online charts.
A step toward safe and reliable autopilots for flying
A new AI-based approach for controlling autonomous robots satisfies the often-conflicting goals of safety and stability.
New tool helps people choose the right method for evaluating AI models
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.
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 use AI to identify similar materials in images
This machine-learning method could assist with robotic scene understanding, image editing, or online recommendation systems.
A better way to study ocean currents
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.