Train a Neural Network Using Unsupervised Running

The idea is that you would train a system in this self-supervised manner with tons and tons of data. There's no limit to how many YouTube videos you can make the machine watch. And then what you would do is whenever a particular task comes in, like learning to drive a car or recognizing particular objects,. You use that representation as input to train that trajectory for your supervised network. Could we build machines at some point that will be as intelligent as humans in all those tasks that humans are intelligent in? The answer is, of course, there's no question. It's a matter of time.