RADIAL BASIS FUNCTION NETWORKS LEARNING TO SOLVE APPROXIMATION PROBLEMS
Journal Title: International Journal of Civil Engineering and Technology - Year 2019, Vol 10, Issue 3
Abstract
The purpose of the paper is the development and experimental study of new fast learning algorithms for radial basis function networks in solving approximation problems. To learn radial basis function networks, algorithms based on first-order methods have been developed for the first time: gradient descent with a pulse, Nesterov’s accelerated gradient algorithm and RMSProp in combination with Nesterov’s accelerated gradient. The advantages of sequential adjustment of parameters in each iterative cycle of network training are shown. The implementation of the Levenberg-Marquardt method for training radial basis function networks has been developed. With the help of the Levenberg-Marquardt method, the same results can be achieved as with the more complex algorithm of the method of trust regions. The developed algorithms have been experimentally studied
Authors and Affiliations
V. FILIPPOV, L. ELISOV, V. GORBACHENKO
Keywords
Related Articles
- EP ID EP46417
- DOI -
- Views 192
- Downloads 0
ANALYSIS OF REDUCTION IN PEDESTRIAN WAITING TIME FOR CROSSING ROUNDABOUT
The purpose of this study is to minimize pedestrian waiting time to cross the roundabout. This study employed an analytical hierarchy process for crossing points at the roundabout. AHP decision making of level 1-3 micr...
USE OF ARTIFICIAL NEURAL NETWORKS FOR SIMULATING ADHAIM RIVER BASIN, IRAQ
Adhaim River is one of Tigris river tributaries, contributing by 5555% of the Tigris River yield, with annual flow rate of 0.832 BCM. To simulate Adhaim River flow, Artificial Neural Networks (ANNs) was used, 21 years’...
CLUSTER APPROACH TO MANAGEMENT OF COMPETITIVENESS OF THE REGIONAL ECONOMY
For Russia, increasing the innovative activity of industrial enterprises is one of the most important strategic tasks, the solution of which depends on economic growth, business development, the level of welfare of the...
THE USE OF INTERNET OF THINGS FOR THE SUSTAINABILITY OF THE AGRICULTURAL SECTOR:THE CASE OF CLIMATE SMART AGRICULTURE
Global climate change has huge effects on the agricultural system and its productivity. Scientists report that changing climatic conditions led to a decrease in global wheat yields by 5, 5% and corn by 3, 8% and that b...
A TWO-DIMENSIONAL SIMULATION OF ULTRASONIC WAVE PROPAGATION IN CONCRETE USING FINITE ELEMENT METHOD
Due to the propagation and interaction characteristics in materials of the ultrasonic wave, it is widely used in the different fields such as medical, mechanical, and construction engineering, specially to detect crack...