A generalization of artificial neuron by substitution of neural convolution to arbitrary multi-parametric function. Weights of synapses have been changed to the set of parameters and a learning algorithm has been modified as well. Even one single “smart neuron” is sufficient for finding...

A principal distinction of neural network based methods of approximation from conventional methods is a hidden inside algorithmic function, which is defined by the neural network topology and is enough sophisticated to make appropriate fitting process. There is a new construction named...

We prove that every Souslin set in R contains a universal measure zero set with the same Hausdorff dimension and that each metric space contains a universal measure zero set with Hausdorff dimension no less than the topological dimension of

A principal distinction of neural network based methods of approximation from conventional methods is a hidden algorithmic function inside, which is defined by a neural network topology and is enough sophisticate constructed to make appropriate fitting process. There is new construction named a...

High uncertainty of AI formalization leads to misunderstanding and wrong activity. Finite number of words, being implemented somewhere else, creates unacceptable scientific environment, which leads to wrong conclusions. The problem of correct terminological extension from common area to the very...

Traditional forecast in technical analysis, based on time series extrapolation, should be substituted by more generic for human beings forecast by repeated situations. This means circadian and circannual rhythms and any typical behavior, which is analyzed and stored in “whole life” memory....

Известно, что классический метод обучения искусственной нейронной сети, построенной по принципу перцептрона Розенблатта, является модификацией метода решения...

In this paper we obtain sufficient conditions for the existence of a stable set of a weak tournament. We also provide necessary and sufficient conditions for unique stable sets as well as necessary and sufficient conditions for the stable sets to coincide with cores

It is known that, if two random vectors normally distributed have the same correlation matrix, then they have the same copula. It is shown in this paper that, in fact, the reverse is also true. This result will be applied to a special case. It will also be shown under a certain condition the...

It is known that, if two random vectors normally distributed have the same correlation matrix, then they have the same copula. It is shown in this paper that, in fact, the reverse is also true. This result will be applied to a special case. It will also be shown under a certain condition the...