Complementary Neural Networks for Managing Innovation Projects

The modelling of neural networks for managing project innovation projects under uncertainty (observability, unverified information and imperfection of loss estimation methods) is considered. The principles and methods of forming innovation projects are defined. The properties of neural networks concerning the parallel processing of information, self-organization, training, generalization, etc. are determined. The general model of the neural network, its elements and training techniques are given. The concepts of neural network and complementarity classes are introduced. The concept of complementary neural network architecture is defined. Within the networks which are determined by elements of the complementary artificial neural network and a signature that forms classes of operations of the neural networks concerning innovation projects.