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 111
- Downloads 0
STEINER NETWORK PROBLEM IN VIEW OF ENERGY COSTS
The optimization method for the Steiner pipeline network based on dynamic decomposition.
A LOCAL ONE-DIMENSIONAL SCHEME FOR PARABOLIC EQUATION OF GENERAL FORM, DESCRIBING MICROPHYSICAL PROCESSES IN CONVECTIVE CLOUDS
This paper considers a locally one-dimensional scheme for a parabolic equation of general form in a p-dimensional parallelepiped.To describe coagulation processes in the cloud, the equation under study involves a non-loc...
FORMULATION AND METHOD OF SOLVING CERTAIN BOUNDARY VALUE PROBLEMS FOR A CLASS OF EQUATIONS THIRD ORDER PARABOLIC-HYPERBOLIC TYPE
This paper studies the methods of investigation of some boundary value problems for a class of parabolic-hyperbolic equations of the third order in the hexagonal concave areas that take advantage of the study of problems...
RANK OPTIMIZATION FOR FLOW NETWORKS
In this paper we present an algorithm for constructing an optimal P-rank flow network in a specified redundant geometric graph with potential links of nodes.
MODELING OF CHOICE LEADERSHIP HIGH SCHOOL OPTIMUM DECISIONS AGREED UPON WITH DRIVING WITH MANAGED SOLUTIONS ITS AFFILIATES
The paper considers the model of choice by high-school optimal solutions for the distribution of sets of entrants in its branches.