Deep Learning is a subset of machine learning. Deep learning takes a raw undefined set of data and parses the data to learn about the the data set being trained. Since deep learning doesn't require a programmer to readjust the algorithm, it requires a large data set in order to for the algorithm to perform better.

The large sets of data is calculated through a untrained neural network. In the process, the weight of each layer is adjusted to recognize important features of the data. Since there are many permutation between the layers, this calculation requires high computational power.