ANNs are networks of artificial neurons and have a biological blueprint. Leaning on biology, an artificial neuron is an object that reacts to one or more stimuli, depending on how strongly it is activated or the stimulus is weighted. An ANN basically consists of an input layer and an output layer. In between are hidden layers or activity layers. As a rule, ANNs need to be trained before they can solve problems. In the process, a certain algorithm or the neural network weights the connections of the neurons on the basis of predefined learning material and learning rules until it has reached or developed a certain learning goal.

See also:

• feed forward neural network (FFNN)
• recurrent neural network (RNN)
• deep neural network (DNN)

ETSI GR ENI 004 computing system that learns to perform functions by using artificial neurons that take the form of a directed, weighted graph.

NOTE: An ANN learns to perform a function by analysing examples (i.e. training data) instead of being programmed to perform a task.