Goto

Collaborating Authors

 Floyd County


Cheaper Robots are Helping Small Businesses Survive

#artificialintelligence

The robotics wave began sweeping into automobile and other plants decades ago, stopping short of shops staffed with a relative handful of people. Many businesses couldn't afford the contraptions, which weren't designed to squeeze into tight spaces or operate very close to human beings. A Rethink Robotics Inc. Baxter robot operated by DHL, a unit of Deutsche Post AG. Technological advances have made industrial robots more compact and kinder. Collaborative models, members of a new generation called cobots, have sensors to prevent them from harming real-life colleagues.


Improvisation and Learning

Franklin, Judy A.

Neural Information Processing Systems

This article presents a 2-phase computational learning model and application. As a demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase 1 of training, recurrent back-propagation trains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation.


Improvisation and Learning

Franklin, Judy A.

Neural Information Processing Systems

This article presents a 2-phase computational learning model and application. As a demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase 1 of training, recurrent back-propagation trains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation.


Improvisation and Learning

Franklin, Judy A.

Neural Information Processing Systems

This article presents a 2-phase computational learning model and application. Asa demonstration, a system has been built, called CHIME for Computer Human Interacting Musical Entity. In phase 1 of training, recurrent back-propagationtrains the machine to reproduce 3 jazz melodies. The recurrent network is expanded and is further trained in phase 2 with a reinforcement learning algorithm and a critique produced by a set of basic rules for jazz improvisation.