Hacker News new | ask | show | jobs
by nicolashahn 3080 days ago
To me it looks like they just took a bunch of specialized NN classifiers and glued them together. Not to belittle their work, this is still impressive and an important step towards generalized machine intelligence, but we're still a very long way off.

The next level above this would be to give it some input and without telling the classifier what to do with it, it decides which task it's supposed to do on its own, and then executes.
2 comments
sdenton4 3079 days ago
That actually seems like a rather higher bar than /we/ have to deal with. Image, auditory, touch and taste data come in on distinct signal paths before going to higher-level feature processing.
link
larister 3079 days ago
True in normal conditions, but our neocortex is highly adaptable. I can’t remember the studies, but there have been cases where a grid of actuators was taped to the body of a blind man and hooked up to a camera mounted on his head. In time, he was able to “see” edges based on the signals coming from his skin.
link
mod 3079 days ago
That's amazing.

I guess probably the orientation didn't even matter. So likely, you could seamlessly wear something like that on a patch of skin that stayed out of your way (on your back, perhaps).

link
hndamien 3077 days ago
This is essentially how cochlear implants work. Just get a usable signal to the brain (early in life) and let the brain sort out what to do with the information.
link
zo1 3079 days ago
It's actually a little tab that the blind person puts on their tongue. Link below.

https://www.popsci.com/fda-allows-marketing-device-lets-blin...

link
leoc 3079 days ago
That's the current model, the Brainport. The original was indeed a chair, back in the late '60s, and there were several users. https://en.wikipedia.org/wiki/Paul_Bach-y-Rita
link
zo1 3072 days ago
Nice find, I didn't know about it. Thanks for the link!
link
ratsimihah 3080 days ago
Wouldn't you "just" need to train a classifier on top to select the best fitting model? Or use ensemble learning? I dunno. My point is that it wouldn't be much more generalized even without that input.
link
nicolashahn 3080 days ago
Yeah, that would just be one step out of the however dozens/hundreds/thousands more to go before AGI.
link