オープンデータとプログラミング

単一摂動は、深い学習 をだますことができます。|A Single Perturbation Can Fool Deep Learning

オープンデータ関連のニュースです。

http://www.i-programmer.info/news/105-artificial-intelligence/10629-a-single-perturbation-can-fool-deep-learning.html

日本語

TranslateApiException: Cannot find an active Azure Market Place Translator Subscription associated with the request credentials. : ID=0642.V2_Json.Translate.3F4FD68D
続きを読む…

English

If you have been reading our reports on adversarial images, the headline should come as no surprise. What is a surprise is the way that AI researchers are regarding such images as security threats rather than a deep insight into the way neural nets work. It was a surprise when adversarial images were discovered. Put simply you can work out a small valued image, a perturbation, that when added to an existing correctly classified image will cause it to be misclassified even though a human can see no difference. It was hinted at the such perturbations disturbed the classification of a range of neural networks and perhaps even other machine learning approaches in the same way.
Read more…

Comments are closed.