Researchers Fooled a Google AI Into Thinking a Rifle Was a Helicopter

Researchers Fooled a Google AI Into Thinking a Rifle Was a Helicopter Published on December 26, 2017 at 12:30PM An anonymous reader shares a Wired report: Algorithms, unlike humans, are susceptible to a specific type of problem called an “adversarial example.” These are specially designed optical illusions that fool computers into doing things like mistake …

Continue reading “Researchers Fooled a Google AI Into Thinking a Rifle Was a Helicopter”