How to trick a neural network! By Julia Evans I used to think neural networks were magical black boxes that I could never understand. And they kind of are! But in this talk, we're going to trick an awesome smart neural network, trained by Google, into thinking a panda is a vulture. Live. And tricking something is the first step towards understanding it! No prior understanding of neural networks or machine learning required. Help us caption & translate this video! http://amara.org/v/K6ut/