How Deep Learning Is Different From Previous Approaches to Machine Learning

The process of figuring out what are the characteristics in the data set that actually matter is now automated. Unlike previous approaches to machine learning where you had, you know, relatively large complicated algorithms to detect all these individual features, deep learning uses much, much simpler sort of atomic type algorithms for each node in the neural network. That means it takes a lot more of them to build up a sophisticated enough neural network but also requires a tremendous amount of data examples.