It's Surprisingly Easy to Make AI Think a Taxi Is a Vacuum Cleaner

Technologists like to put machine learning on a pedestal, exalting its ability to complement and even exceed human labor, but these systems are far from perfect. In fact, they are still tremendously vulnerable to self-owns. A research paper from January details how just how easy it is to trick an image recognition…

Read more...



from Gizmodo https://ift.tt/2UGrlso


EmoticonEmoticon