Multiple Network Systems Minos Modules Task Division and Module Discrimination

It is widely considered an ultimate connectionist objective to incorporate neural net works into intelligent systems These systems are intended to possess a varied re pertoire of functions enabling adaptable interaction with a non static environment The rst step in this direction is to develop various neural network algorithms and models the second step is to combine such networks into a modular structure that might be incorporated into a workable system In this paper we consider one aspect of the second point namely processing reliability and hiding of wetware details Pre sented is an architecture for a type of neural expert module named an Authority An Authority consists of a number of Minos modules Each of the Minos modules in an Authority has the same processing capabilities but varies with respect to its par ticular specialization to aspects of the problem domain The Authority employs the collection of Minoses like a panel of experts The expert with the highest con dence is believed and it is the answer and con dence quotient that are transmitted to other levels in a system hierarchy