Brain machines that can learn are created

GAINESVILLE, Fla., June 26 (UPI) -- U.S. scientists say they've created algorithms that can help devices known as brain-machine interfaces to learn as they are used.

Brain machines might someday be used to help paralyzed patients and amputees control prosthetic limbs with just their thoughts. University of Florida researchers have devised a way for the computerized devices to not only translate brain signals into movement, but also to evolve as the interface learns.

Instead of simply interpreting brain signals and routing them to a robotic hand or leg in a kind of one-way conversation, the researchers said the new interface would adapt to a person's behavior over time and use the knowledge to help complete tasks more efficiently.

"In the grand scheme of brain-machine interfaces, this is a complete paradigm change," said Assistant Professor Justin Sanchez, the study's senior author. "This idea opens up all kinds of possibilities for how we interact with devices."

Sanchez, Professors Jose Principe and Jose Fortes, and doctoral students Jack DiGiovanna and Babak Mahmoudi report their research online in the journal IEEE Transactions on Biomedical Engineering.