Simulation and Research for Forward Neural Networks Modeling

Author

Li Qiang ; Zhang Yanxue

Author_Institution

Dept. of Network Technol., Tianjin Electron. Inf. Coll., Tianjin, China

fYear

2014

fDate

25-26 Oct. 2014

Firstpage

644

Lastpage

649

Abstract

This paper presents analysis and experiments for Forward Neural Networks (FNN) modeling based on software simulation. First, we illustrate this modeling method in detail. Then the algorithm flow charts of four learning algorithms, including Back Propagation (BP), Modified BP (MBP), Davidon Least Square based algorithm and Damping Least Square based algorithm are given. In addition, a simulation software for training and testing FNN is developed using these algorithms. In the last, we compare and analyze the performance of these four algorithms based on simulation experimental results.

Keywords

backpropagation; digital simulation; flowcharting; least squares approximations; neural nets; Davidon least square based algorithm; FNN; FNN testing; FNN training; MBP; back propagation; damping least square based algorithm; flow charts; forward neural network modeling; learning algorithms; modified BP; software simulation; Algorithm design and analysis; Approximation algorithms; Damping; Neural networks; Signal processing algorithms; Software algorithms; Training; BP; Damping LS; Davidon LS; FNN; MBP; Simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation (ICICTA), 2014 7th International Conference on

Conference_Location

Changsha

Print_ISBN

978-1-4799-6635-6

Type

conf

DOI

10.1109/ICICTA.2014.160

Filename

7003623