Mikio Braun
@mikiobraun
RT @huitseeker: Yup, it's replicated (and fun!) research now. Deep Neural Networks Are Easily Fooled arxiv.org/abs/1412.1897 (after http://t…
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual...
arxiv.org