A team of researchers used neural implants to enable a paralyzed person to type using their imagination.
The implants were placed in the premotor cortex, an area that is thought to be involved in forming the intentions to perform movements.
Catching the signals for intentions produced clearer results than trying to catch the signals for the movements themselves.
The researchers trained a neural network to estimate the probability of a signal corresponding to each letter, resulting in a system that could type at roughly 90 characters per minute with an error rate of about 5 percent.