For a neural network it is essential in which order the separate neurons receive and process the input and production the results. We distinguish two model classes:

1. Synchronous activation:-All neurons modify their values synchronously,i.e. they at the same time calculate network inputs, activation and also output, and pass them on. Synchronous activation corresponds closest to its biological counterpart, but it is to be implemented in hardware only effective on certain parallel computers and especially not for feedforward networks. This order of activation is easily the most generic and can be used with networks of arbitrary topology.