There is no universally accepted definition of ANN. But perhaps most people in the field would agree that ANN is a network of many simple processors, each possibly having a small amount of local memory. These units are connected by communication channels which carry numeric data, encoded by any of the various means. The units operate only on their local data and on the input they receive via the connections. The restrictions to local operations are often relaxed during training

Some ANNs are models of biological neural networks. Much of the inspiration for the field of ANNs came from the desire to produce artificial systems capable of sophisticated, perhaps “intelligent” computations in the same way human brain routinely performs organs. The effectors are controlled and give human responses in the form of delivery actions. Thus we have a 3-stage system consisting of receptors, neural network and effectors, in control of organisms and its actions.

ANN is a system composed of many simple processing elements operating in parallel whose function is determined by network structure, connection strengths, and the processing performed at computing elements or nodes.