Definition: neural network

An artificial intelligence (AI) modeling technique loosely based on the behavior of neurons in the human brain. Neural networks are used in image processing, robotics, diagnosing, forecasting and many other disciplines. Unlike regular applications that are programmed to deliver precise results (if this, do that), neural networks are trained with millions and billions of examples of media (text, images, etc.).

Neural networks have a much more complicated architecture than normal business logic. They are the foundation of "machine learning" and "deep learning." See neuron, deep learning, GAN, neuroinformatics, machine learning, TensorFlow and AI.

To learn how a neural network actually performs recognition, see convolutional neural network. The following neural network diagrams from the Asimov Institute in the Netherlands reveal the huge variety of architectures that have been conceived.

Neural Network Architectures

AI networks are one of the most researched areas of computing in the 21st century. (Images courtesy of Fjodor van Veen and Stefan Leijnen (2019). The Neural Network Zoo, www.asimovinstitute.org/neural-network-zoo)