Devices known as brain-machine interfaces could someday be used regularly to help paralyzed patients and amputees control prosthetic limbs with just their thoughts. University of Florida researchers are developing a way for computerized devices not only to translate brain signals into movement but also to evolve with the brain as it learns. Instead of just interpreting brain signals and routing them to a robotic hand or leg, this type of brain-machine interface would learn from a person's behavior over time and use the knowledge to complete the subsequent tasks more efficiently, sort of like an assistant, say UF College of Medicine and College of Engineering researchers who developed a model system and tested it in rats.

Until now, brain-machine interfaces have been designed in a way with the brain issuing commands and the computer just following them. The system UF engineers created actually allows the computer to better its performance learning from prior commands.

Source