News for hackers. Stuff that matters.
Re:Differentiable Neural Computers by empath75 on Thursday October 13, 2016 @11:17AM (#12701283)
Feeding mp3s to an image recognition neural net. And as soon as I typed that, I want to try it.
Re:Differentiable Neural Computers by modeless on Thursday October 13, 2016 @01:45PM (#12702606)
Actually, in the architecture you described, if there is a planning net that's connected to image net and an audio net, rather than feeding audio to the image net I think synesthesia would be better modeled by feeding the output of the audio net into the image net's input on the planning net. If that makes sense.
Re:Differentiable Neural Computers by Senji on Thursday October 13, 2016 @02:18PM (#12702841)
Not the output. Making several single connections from intermediate layers from the different nets.
Re:Differentiable Neural Computers by dharma1 on Thursday October 13, 2016 @02:11PM (#12702788)
CNNs can actually be used for audio tasks too, on spectrograms
Re:Differentiable Neural Computers by Senji on Friday October 14, 2016 @05:51AM (#12707038)
It's how some guys defeated the first iteration of recaptcha's audio mode. Then google replaced it with something very annoying to use even for humans.