Major Breakthrough in Direct Neural Interface 308
jd writes "In a major breakthrough, neurologists are reporting that they can decypher neurological impulses into speech with an 80% accuracy. A paralyzed man who is incapable of speech has electrodes implanted in his brain which detect the electrical pulses in the brain relating to speech. These signals are then fed into computers which covert these pulses into signals suitable for speech synthesis. As a biotech marvel, this is astonishing. Depending on the rate of development it is possible to imagine Professor Hawking migrating to this, as it would be immune to any further loss of body movement and would vastly accelerate his ability to talk. On the flip-side, direct brain I/O is also a major step towards William Gibson's Neuromancer and other cyberpunk dark futures."
More info (Score:5, Informative)
They have hooked up to 41 neurons and:
Re:Really accurate? (Score:5, Informative)
Sensitivity = percentage number of correct identifications
Specificity = corresponding percentage of incorrect identifications at each measured sensitivity.
Probably they can get up to 90%, but from experience I would say the rate of false positives at this sensitivity likely is moving towards exponential increase. It's better to stop at 80%, at least when something is in the early stages.
This is just guessing of course, I have no understanding of their research, but going from my own work on non linearly separable sets, I'd say this is what's happening.
can still communicate (Score:5, Informative)
he could blink. that's it. yes or no. and with that ability, letter by letter, he wrote a book (with the help of some very patient nurses/ assistants)
it's coming out as a movie soon too i think
Re:What? (Score:5, Informative)
80% accuracy... (Score:3, Informative)
What do you want to decipher today?
Research posters (Score:5, Informative)
http://migrate.speechprosthesis.org/DNN2/SpeechProsthesisHome/tabid/52/Default.aspx [speechprosthesis.org]
There's also a nice blog entry on this over at Neurophilosophy:
http://scienceblogs.com/neurophilosophy/2007/11/speech_prosthesis.php [scienceblogs.com]
Re:what if (Score:3, Informative)
But, breaking jaws or limbs during or after boot, ehh, I won't go that far. Never know when later on you end up a casualty of friendly fired. Grudges can be held for years, resurfacing when you least expect.
Remember the race riots of the 70's in the USN? Sailor stabbing one another in their racks (bunks, for you land lubbers)?; sailors ending up in sea bags and tossed overboard for witnessing drug deals at sea?; sailors being cold-cocked/whacked over the head with a dogging pipe or dogging wrench from behind?; the sailor in the 80's who was restrained by multiple shipmates who "raped" him with a pneumatic grease gun's tube and pumped the mil-spec stuff in him, ruining his innards? (they got Leavenworth for that);
There's a reason you DON'T whack the shit out of people or break limbs. I swear, had that happened to me, I'd have become a serial killer, maybe. Not out of weakness, but out of revenge.
Fortunately, I kept myself just inside the line of nerd/annoying-but-not-threatening. How? I learned WHEN not to report certain violations. I never turned in people from gambling, slushing, or the like, but I DID prep my pistol to deter a multi-occasion deserter from deserting on my watch when the quarterdeck watch of another ship was watching him and us. Had I looked the other way, they'd have reported seeing the Roving Patrol walking away from someone with a seabag shimmying down the stern quarter mooring line.
No, the DUR (Dicked-Up Recruits) you weed out despite the expense of acquisition. I only get physical for DEFENSE, not training or offense. But, then I wasn't a Marine or army soldier, either. Nor did I train for SEALs or the like, so fortunately, I was never really NEAR the level of intense training USMC/Army guys might be under.
Re:That extra 20% probably wasn't important anyway (Score:1, Informative)
http://crastinate.jonwiley.com/?p=33 [jonwiley.com]
Vinge, not Gibson (Score:4, Informative)
If you haven't read it, I highly recommend it. Read True Names to get a notion of the profound visionary Vernor Vinge is. (Remember it was published in 1981).
Then read Rainbows End with your newfound respect for Vinge's powers of prognostication, and recognize that you're seeing into the near future.
summary is blatantly misrepresentative! (Score:1, Informative)
summary says: neurologists are reporting that they can decypher neurological impulses into speech with an 80% accuracy.
article says: Although the data is still being analysed, researchers at Boston University believe they can correctly identify the sound Mr Ramsay's brain is imagining some 80% of the time. In the next few weeks, a computer will start the task of translating his thoughts into sounds.
come on. the article implys that this is already being done, with 80% accuracty. seems to me, they just think it's going to work, and haven't even started trying it yet.
Re:Sadly more likely... (Score:2, Informative)
No one sees what I do every day to help myself function, or knows what they are seeing if they do notice. My environment is very very controlled. When I was in school I could study for about 30 minutes at a time, then I needed a break. I could study one more time for 30 minutes, and then I needed a nap. My classes had to be at certain times of the day, and in a certain order. Everything I want to retain has to be written down, obsessively, over and over. I have to be able to see it, or spoken words (lectures) mean nothing to me. I struggle every day with sound and auditory stimuli. This is permanent damage. Brain injury never goes away; in my case, I could learn how to work with it.
As someone who works with these sorts of injuries, you should be first on the block to understanding that every brain is different. It wasn't a trivial case and it wasn't just "positive thinking". It was, and is, a hell of a lot of work.