CASCADING OF NEURAL NETWORKS

Abstract

here are technologies that allow combining several neural modules into a single neural network. The cascading procedure is designed to interface neural networks on data flow and error back propagation. This allows the use of the generic method for forward propagation modular networks training with arbitrary structure. The mathematical model of cascading neural networks is given. In case of cascade connection modules, the neural network learning can be made with different speeds of training for the incoming modules. Next, the article presents the tasks based on neural networks. Features that the task should have in order to justify the application of neural networks, and the neural network could solve it, are: - there are no algorithm or known principles for tasks solution, but there is a sufficient number of examples; - the task is characterized by large volumes of input data; - the data is either incomplete or redundant, noisy, partially contradictory. Neural networks are well suited for image recognition and solving prob-lems of classification, optimization and forecasting.