Computer Sciences

New 'bandit' algorithm uses light for better bets

How does a gambler maximize winnings from a row of slot machines? This is the inspiration for the "multi-armed bandit problem," a common task in reinforcement learning in which "agents" make choices to earn rewards. Recently, ...

Machine learning & AI

AI models are powerful, but are they biologically plausible?

Artificial neural networks, ubiquitous machine-learning models that can be trained to complete many tasks, are so called because their architecture is inspired by the way biological neurons process information in the human ...


Training robotic arms with a hands-off approach

Humans often take their fine motor abilities for granted. Recreating the mechanical precision of the human body is no easy task—one that graduate students in CMU's Mechanical Engineering Department hope to simplify through ...

page 1 from 21