| Thread Tools |
14th January 2019, 11:20 | #1 |
[M] Reviewer Join Date: May 2010 Location: Romania
Posts: 148,597
| IBM gets neural networks to conceptually think MIT-IBM Watson AI Lab find GANs a powerful tool Boffins working at MIT-IBM Watson AI Lab have been playing around with GANs, or generative adversarial networks, because they are providing clues about how neural networks learn and reason. For those who came in late, GANs have been used for AI painting, superimposing celebrity faces on the bodies of porn stars and other cultural feats. They work by pitting two neural networks against each other to create realistic outputs based on what they are fed. Feed one lot of dog photos, and it can create new dogs; feed it lots of faces, and it can create new mug-shots. Researchers from the MIT-IBM Watson AI Lab realised GANs are also a powerful tool: because they paint what they’re “thinking,” they could give humans insight into how neural networks learn and reason. This has been something the broader research community has sought for a long time—and it’s become more important with our increasing reliance on algorithms. David Bau, an MIT Ph.D. student who worked on the project, told MI,T Technology review that there was a chance for the team to learn what a network knows from trying to re-create the visual world. So the researchers began probing a GAN’s learning mechanics by feeding it various photos of scenery—trees, grass, buildings, and sky. They wanted to see whether it would learn to organise the pixels into sensible groups without being explicitly told how. Stunningly, over time, it did. By turning “on” and “off” various “neurons” and asking the GAN to paint what it thought, the researchers found distinct neuron clusters that had learned to represent a tree, for example. Other clusters represented grass, while still others represented walls or doors. In other words, it had managed to group tree pixels with tree pixels and door pixels with door pixels regardless of how these objects changed colour from photo to photo in the training set. https://fudzilla.com/news/ai/47937-i...eptually-think |
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
'MindGamers' clip shows off the dangers of wireless neural networks | Stefan Mileschin | WebNews | 0 | 2nd March 2017 06:38 |
Google AI experiments help you appreciate neural networks | Stefan Mileschin | WebNews | 0 | 17th November 2016 19:59 |
Photo editor uses neural networks to airbrush like a pro | Stefan Mileschin | WebNews | 0 | 30th September 2016 09:40 |
Neural networks are powerful thanks to physics, not math | Stefan Mileschin | WebNews | 0 | 13th September 2016 07:57 |
Google's using neural networks to make image files smaller | Stefan Mileschin | WebNews | 0 | 24th August 2016 10:20 |
This is what it looks like when a neural net colorizes photos | Stefan Mileschin | WebNews | 0 | 5th April 2016 08:08 |
Google is using neural networks to improve Translate | Stefan Mileschin | WebNews | 0 | 13th March 2016 06:53 |
OCZ Neural Impulse Actuator Review | jmke | WebNews | 0 | 18th November 2008 10:01 |
OCZ's Neural Impulse Actuator | Massman | WebNews | 0 | 28th June 2008 14:55 |
OCZ Neural Impulse Actuator Tested | jmke | WebNews | 0 | 2nd June 2008 09:30 |
Thread Tools | |
| |