Deep learning is based on the branch of machine learning, which is a subset of artificial intelligence. Since neural networks imitate the human brain and so deep learning will do. In deep learning, nothing is programmed explicitly. Basically, it is a machine learning class that makes use of numerous nonlinear processing units to perform feature extraction as well as transformation. The output from each preceding layer is taken as input by each one of the successive layers.

If you're keeping up to date on technology news, you're probably seeing references to machine learning everywhere, and for good reason: machine learning is an integral component of the way that computers process information. Machine learning is all around us, informing our day to day lives from the way we navigate Google maps right down to the way we check our inboxes. Here's a quick explainer to get you up to date:

Machine learning differs from human learning, insofar as the machine only knows what you tell it: A computer can't express curiosity or make inferences. For example, if you watch a lot of scifi movies on Netflix, you might find Stranger Things in your suggestion queue. But it's only a matter of math, based on Netflix's data alone -- if you've never told Netflix that you love documentaries, or rated one highly, the system will likely never show you one.