Problem of Сonstructing the GMDH Neural Networks with Active Neurons

Abstract

Characteristics of the existing neural networks of GMDH with active neurons are given and their main advantages and disadvantages are analyzed. Two approaches of increasing the efficiency of inductive construction of complex system models from statistical data based on a new hybrid GMDH neural networks with active neurons using methods of computational intelligence are proposed. The effectiveness of these networks is compared with classical approaches to artificial inductive modelling tasks (noisy linear and nonlinear models).