Analysis of iterative learning algorithms for the multilayer perceptron neural network

Baček, Tomislav and Majetić, Dubravko and Brezak, Danko and Kasać, Josip (2011) Analysis of iterative learning algorithms for the multilayer perceptron neural network. = Analysis of iterative learning algorithms for the multilayer perceptron neural network. In: The 22nd DAAAM International Symposium "Intelligent Manufacturing & Automation: Power of Knowledge and Creativity", 23-26.11.2011., Beč, Austrija.

[img]
Preview
Text
Analysis of Iterative Learning Algorithms for the Multilayer Perceptron Neural Network.pdf - Submitted Version Jezik dokumenta:English

Download (1MB) | Preview
Official URL: https://www.bib.irb.hr/536908

Abstract

In this paper, a comparison of different algorithms used in the training of a multilayer feedforward neural network is presented. Tested algorithms, which are of the first and the second order, include both local and global adaptation techniques. Prediction of nonlinear dynamic Glass-Mackey system is used as a benchmark problem. To improve training speed and efficiency, bipolar sigmoidal activation function with adaptive gain parameter is used. Furthermore, modification of random weight initialization is proposed.

Item Type: Conference or Workshop Item (Lecture)
Keywords (Croatian): static neural network, adaptive activation function, prediction, nonlinear chaotic system
Subjects: TECHNICAL SCIENCE > Mechanical Engineering
Divisions: 900 Department of Robotics and Production System Automation > 910 Chair of Engineering Automation
Indexed in Web of Science: No
Indexed in Current Contents: No
Citations SCOPUS: 0 (19.09.2018.)
Date Deposited: 27 Oct 2015 08:02
Last Modified: 19 Sep 2018 12:16
URI: http://repozitorij.fsb.hr/id/eprint/4836

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

Nema podataka za dohvacanje citata