Some of the well-known and widely accepted definitions of deep learning are as follows:
- It is a subset of ML.
- It uses a cascade of multiple layers of (non-linear) processing units, called an artificial neural network (ANN), and algorithms inspired by the structure and function of the brain (neurons). Each successive layer uses the output from the previous layer as input.
- It uses ANN for feature extraction and transformation, to process data, find patterns, and develop abstractions.
- It can be supervised (for example, classification) or unsupervised (for example, pattern analysis).
- It uses gradient-descent algorithms to learn multiple levels of representations that correspond to different levels of abstraction and the ...