Publication detail

Neural network learning algorithms comparison on numerical prediction of real data

ŠTENCL, M. ŠŤASTNÝ, J.

Original Title

Neural network learning algorithms comparison on numerical prediction of real data

Type

conference paper

Language

English

Original Abstract

In this paper we concentrate on prediction of future values based on the past course of a variable, Traditionally this task is solved using statistical analysis - first a time-series model is constructed and then statistical prediction algorithms are applied to it in order to obtain future values. This paper describes two learning algorithms for training Multi-layer perceptron networks, widely known Back propagation learning algorithm and Levenberg- Marquardt algorithm. Both of these methods are applied to solve prediction of real numerical time series represented by Czech household consumption expenditures. Tested dataset includes twenty-eight observations between the years 2001 and 2007. The observations are represented by quarterly data and the goal is to predict three future values for first three quarters of 2008. Predicted values of both experiments are compared with measured values. In the next step, a comparison of neural network topology efficiency regarding to learning algorithms is made.

Keywords

Back Propagation, Levenberg-Marquardt, Prediction of Time Series, Neural Networks

Authors

ŠTENCL, M.; ŠŤASTNÝ, J.

RIV year

2010

Released

23. 6. 2010

ISBN

978-80-214-4120-0

Book

Mendel 2010

Edition number

16

Pages from

280

Pages to

285

Pages count

6

BibTex

@inproceedings{BUT34565,
  author="Michael {Štencl} and Jiří {Šťastný}",
  title="Neural network learning algorithms comparison on numerical prediction of real data",
  booktitle="Mendel 2010",
  year="2010",
  number="16",
  pages="280--285",
  isbn="978-80-214-4120-0"
}