Re:“How do I choose not to share my account information with...
by nostrademons on Friday August 26, 2016 @02:57PM
(#12368469)
Markov chains aren't really relevant here - they're a way to generate random but "seemingly plausible" data - but yes, there is a way to fool the type of convolutional neural networks used in image recognition. Paper here:
http://www.evolvingai.org/fooling