ON THE OPTIMIZATION OF THE CONSTRUCTIVE METHOD OF TRAINING NEURAL NETWORKS
Journal Title: Вестник КРАУНЦ. Физико-математические науки - Year 2018, Vol 3, Issue
Abstract
The article suggests a constructive method for training neural networks in which neurons added just before the current epoch of training assume the main training load on the new class to ensure the stability of the network in relation to learning on new data classes. The results of computational experiments are presented
Authors and Affiliations
Muhamed Kazakov
Keywords
Related Articles
- EP ID EP505515
- DOI 10.18454/2079-6641-2018-23-3-184-189
- Views 102
- Downloads 0
TO THE QUESTION OF SOLVABILITY OF ORDINARY DIFFERENTIAL EQUATIONS OF FRACTIONAL ORDER
We discussed the problem of solvability of initial value problem for one model ordinary differential equation of fractional order. It is shown that the dimension of the kernel depends on the distribution parameters of Dz...
DENOISING OF GEOACOUSTIC EMISSION SIGNALS FROM NATIVE AND TECHNOGENIC NOISES USING THE SPARSE APPROXIMATION METHOD
The approach of geoacoustic emission signals denoising from native and technogenic noises based on sparse approximation method is offered in this paper. The use of this means made it possible to clear geoacoustic emissio...
GLOBAL MARKET FORECAST NANOPOWDERS
We have made a global analysis of the market nanopowders. Based on the available data it can be concluded that the introduction of nano-powders in various spheres of high technologies will occur every year more intensive...
ON SOLVABILITY OF THE BOUNDARY VALUE PROBLEM FOR ONE EVEN-ORDER EQUATION
In this paper boundary-value problem for one even-order equation is studied. The unique solvability of the problem is restored by additional conditions and conditions to domain.
PROBLEM WITH CONDITIONS SAMARA FOR FRACTIONAL DIFFUSION EQUATION IN THE HALF
In this paper, we construct a solution of a nonlocal boundary value problem with the condition Samarskii for a fractional diffusion equation in the half.