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.
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
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.
Researchers create a privacy technique that protects sensitive data while maintaining a machine-learning model’s performance.
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
A new dataset can help scientists develop automatic systems that generate richer, more descriptive captions for online charts.
A new AI-based approach for controlling autonomous robots satisfies the often-conflicting goals of safety and stability.
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.
Researchers develop an algorithm that decides when a “student” machine should follow its teacher, and when it should learn on its own.
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.