quinta-feira, abril 14, 2016

dirty data

One way to visualize what goes on is to turn the network upside down and ask it to enhance an input image in such a way as to elicit a particular interpretation. Say you want to know what sort of image would result in “Banana.” Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana. By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated. 

in, “Inceptionism: Going Deeper into Neural Networks,” Google Research Blog, June 17, 2015

from Hito Steyerl’s A Sea of Data: Apophenia and Pattern (Mis-)Recognition

from Tumblr http://ift.tt/1RXdV5O

Sem comentários: