Applications of MVN and MLMVN

Abstract

In this Chapter, we will consider some applications of MVN and MLMVN. In Chapters 2-5 we have introduced MVN, we have deeply considered all aspects of its learning, we have also introduced MLMVN and its derivative-free backpropagation learning algorithm; finally we have introduced MVN-P, the multi-valued neuron with a periodic activation function and its learning algorithm. We have illustrated all fundamental considerations by a number of examples. Mostly we have considered so far how MVN, MVN-P, and MLMVN solve some popular benchmark problems. It is a time now to consider some other applications including some real-world applications. In Section 6.1, we will consider how MLMVN can be used for solving a problem of blur and its parameters identification, which is of crucial importance in image deblurring. In Section 6.2, we will show how MLMVN can be used for solving financial time series prediction problems. In Section 6.3, we will consider how MVN can successfully be used in associative memories. Some other MVN applications will be observed and some concluding remarks will be given in Section 6.4.