Deep learning is a subset of machine learning, which in turn falls under the broader umbrella of artificial intelligence (AI). The term “deep” refers to the use of deep neural networks—complex structures inspired by the human brain—to process data and make decisions. This post in just a quick introduction to the basics of deep learning.

A deep learning model consists of a neural network with three or more layers. Data enter through the input layer. Hidden layers process and transport data to other layers. The Output layer is the final result or prediction. Deep learning models learn by analyzing massive amounts of information (known as training data). They repeatedly perform a given task, improving their accuracy over time—much like how we study and practice to enhance our skills.

What are some uses of deep learning? One use is self-driving cars. Another use is fraud detection.

Wikipedia says: “In deep learning, each level learns to transform its input data into a slightly more abstract and composite representation. In an image recognition application, the raw input may be a matrix of pixels; the first representational layer may abstract the pixels and encode edges; the second layer may compose and encode arrangements of edges; the third layer may encode a nose and eyes; and the fourth layer may recognize that the image contains a face.”

Wikipedia also says: “Machine learning models are now adept at identifying complex patterns in financial market data. Due to the benefits of artificial intelligence, investors are increasingly utilizing deep learning techniques to forecast and analyze trends in stock and foreign exchange markets.”