MIT touts new mind-to-machine algorithm

Unifying, but not universal, approach

By Lucy Sherriff • Get more from this author

Posted in Science, 4th October 2007 11:20 GMT

Free whitepaper – Optimizing the data center for cost and efficiency

Boffins at MIT are getting ever closer to a direct mind-to-machine link that would translate a person's thoughts into instructions for a machine. The university is developing the technology so a paralysed person might be able to operate a prosthetic purely by using their mind.

There are lots of teams working in similar areas. The notion that brain activity should be monitored and used to derive a person's intentions is not new. But MIT says its algorithm will work with all the rest of the research that has already been done, rather than adding a new technique to the pile.

Lakshminarayan "Ram" Srinivasan, lead author of a paper on the subject, said: "The work represents an important advance in our understanding of how to construct algorithms in neural prosthetic devices for people who cannot move to act or speak...we don't need to reinvent a new paradigm for each modality or brain region."

The graphical model being developed by the MIT researchers would work regardless of which measurement technique is used, he explained.

That being said, there is still work to do before we get to the stage of "thinking" our cars, or entrusting the flying of planes to a brain-to-machine link.

"Translating an algorithm into a fully functioning clinical device will require a great deal of work, but also represents an intriguing road of scientific and engineering development for the years to come," MIT said.

More here. ®

Free whitepaper – PowerEdge M-Series blades I/O guide