The used generalized net will give us a possibility for parallel optimization of feed-forward neural network based on assigned training pairs with variable learning rate backpropagation algorithm.
In this paper we considered a streaming data classification problem. First we introduced a concept of upper and lower envelopes of time series in order to reduce dimensionality of them. Next we merged machine learning tools like feedforward neural networks for selection principal attributes as well as decision rules of the form if … then … for… (More)
The proposed approach is based on the theory of multisets. In the paper we defined a novel measure of remoteness between multisets. There is introduced the definition of perturbation of one multiset by another multiset and/or vice-versa. In general these two measures are different, asymmetrical, so they should not be considered as the distance between… (More)
In this paper we used a generalized net which gives a possibility for parallel optimization of multilayer neural networks. For training the backpropagation algorithm with momentum was considered. We proposed a generalized net model of parallel training of two neural networks with different architectures. The difference between the networks is in the number… (More)
In this paper we introduce e GN-model of the work of Learning Vector Quantization neural networks. The model can be used for the optimization and following the network's behavior in future. Introductions In a series of papers the process of functioning and the results of the work of different types of neural networks have been described by Generalized Nets… (More)
The theory of intuitionistic fuzzy sets is used in this paper for the assessment of the student's knowledge of mathe-matics. The method presented here provides the possibility for the algorithmization of the process of forming the student's evaluations.