학술논문
Approximation-based Estimation of Learning Rate for Error Back Propagation Algorithm
Document Type
Conference
Author
Source
2019 IEEE 23rd International Conference on Intelligent Engineering Systems (INES) Intelligent Engineering Systems (INES), 2019 IEEE 23rd International Conference on. :000065-000070 Apr, 2019
Subject
Language
Abstract
The paper presents a new method for improvement of the Error Back Propagation, one of the most popular algorithms for training artificial neural networks, that is based on the estimation of the learning rate by the approximation of the error of the output error. Experimental studies confirming the effectiveness of the applied method of improving the network learning effectiveness have been presented