Stochastic gradient descent methods are at home in the fields of artificial intelligence, big data and smart data, as well as digital transformation. This term describes a method by which computers can learn quickly and efficiently from large amounts of data.
Imagine a computer is supposed to recognise whether a cat or a dog is visible in a photograph. For the computer to learn this, it must analyse many examples and improve its „decision“ step by step. Stochastic gradient descent helps with this: it doesn't always take all available data at once but looks at randomly selected examples. This saves the computer a lot of time and processing power.
A simple example: imagine a large box full of letters that need to be sorted into „important“ and „not important“. Instead of checking all the letters at once, an employee just looks at a few randomly picked letters, learns from them, and adjusts their sorting method. Over many repetitions, they get better and better without ever having to see every single letter.
In AI and Big Data, the stochastic gradient descent method makes it possible to process huge datasets quickly and draw conclusions from them.
Deutsch 
English (UK)