Naslov
A Comparison of Feed-forward and Recurrent Neural Networks in Time Series Forecasting

Autori
Brezak, Danko ; Baček, Tomislav ; Majetić, Dubravko ; Kasać, Josip ; Novaković, Branko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Conference Proceedings IEEE-CIFEr 2012 / Yager, R. ; Golan, R. - New York (NY) : IEEE Computational Intelligence Society, 2012, 119-124

Skup
IEEE-CIFEr 2012

Mjesto i datum
New York City (NY), Sjedinjene Američke Države, 29.03.2012. - 30.03.2012

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Static neural network; Dynamic neural network; Time series forecasting; Learning algorithms comparison

Sažetak
Forecasting performances of feed-forward and recurrent neural networks (NN) trained with different learning algorithms are analyzed and compared using the Mackey–Glass nonlinear chaotic time series. This system is a knownbenchmark test whose elements are hard to predict. Multi–layer Perceptron NN was chosen as a feed-forward neural network because it is still the most commonly used network in financial forecasting models. It is compared with the modified version of the so-called Dynamic Multi–layer Perceptron NN characterized with a dynamic neuron model, i.e., Auto Regressive Moving Average filter built into the hidden layer neurons. Thus, every hidden layer neuron has the ability to process previous values of its own activity together with new input signals. The obtained results indicate satisfactory forecasting characteristics of both networks. However, recurrent NN was more accurate in practically all tests using less number of hidden layer neurons than the feed-forward NN. This study once again confirmed a great effectiveness and potential of dynamic neural networks in modeling and predicting highly nonlinear processes. Their application in the design of financial forecasting models is therefore most recommended.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA