recentpopularlog in


« earlier   
A neural network can learn to organize the world it sees into concepts—just like we do • MIT Technology Review
Karen Hao:
<p>GANs, or generative adversarial networks, are the social-media starlet of AI algorithms. They are responsible for creating the first AI painting ever sold at an art auction and for superimposing celebrity faces on the bodies of porn stars. They work by pitting two neural networks against each other to create realistic outputs based on what they are fed. Feed one lots of dog photos, and it can create completely new dogs; feed it lots of faces, and it can create new faces. 

As good as they are at causing mischief, researchers from the MIT-IBM Watson AI Lab realized 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.

“There’s a chance for us to learn what a network knows from trying to re-create the visual world,” says David Bau, an MIT PhD student who worked on the project.

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 organize 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 color from photo to photo in the training set. “These GANs are learning concepts very closely reminiscent of concepts that humans have given words to,” says Bau.</p>

OK, so it can group them as concepts. Is that the same as having a concept of them, though?
ai  algorithms  artificialintelligence 
17 hours ago by charlesarthur
GitHub - Bjarten/alvito: Alvito - An Algorithm Visualization Tool for Python
Alvito is a tool for creating sorting and search algorithm visualizations and saving them as GIFs. You can find the alvito class in the
algorithms  python  tools  visualization 
19 hours ago by lena
The Fast Fourier Transform (FFT) and big data
The Fast Fourier Transform got people thinking about big data sets and the need for algorithms to scale well with data size
signal-processing  algorithms 
19 hours ago by Kjaleshire
Biased algorithms: here's a more radical approach to creating fairness
We do care about procedural fairness. Yet substantive fairness often matters more – at least, many of us have intuitions that seem to be consistent with this. Some of us think that presidents and monarchs should have the discretion to offer pardons to convicted offenders, even though this applies legal rules inconsistently – letting some, but not others, off the hook. Why think this is justified? Perhaps because pardons help to ensure substantive fairness where procedurally fair proc...
AI  algorithms  ethics 
22 hours ago by javierruiz
Permutation Algorithms Using Iteration and the Base-N-Odometer Model (Without Recursion)
Scalable Permutations: A Permutation of Agreeable Ideas (PREVIEW)

By Phillip Paul Fuchs
book  cs  math  algorithms 
yesterday by euler

Copy this bookmark:

to read