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 levels form a hierarchy of concepts.
• It achieves great power and flexibility by learning to represent the world as a nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations computed in terms of less abstract ones.

For example, for an image classification problem, a deep learning model learns the image classes in an incremental manner using its hidden layer architecture. 

First, it automatically extracts low-level features such as identifying light or dark regions, and then it extracts high-level features such as edges. Later, it extracts the highest-level features, such as shapes, so that they can be classified. 

Every node or neuron represents a small aspect of the whole image. When put together, they depict the whole image. They are capable of representing the image fully. Moreover, every node and every neuron in the network is assigned weights. These weights represent the actual weight of the neuron with respect to the strength of its relationship with the output. These weights can be adjusted while the models are developed.