Criteria for Best Architecture Selection in Artificial Neural Networks

Çağatay Bal and Serdar Demir

Chapter 12 in Modeling and Advanced Techniques in Modern Economics, 2022, pp 233-294 from World Scientific Publishing Co. Pte. Ltd.

Abstract: Architecture selection in artificial neural networks is a critical process which determines a satisfactory neural network model(s) that will lead to the most accurate results. The architecture that minimizes the difference between the target values of the neural network and the predictions produced by the model represents the best forecasts, namely the most appropriate model. In the literature, there are many common criteria for measuring model performance. In addition, some modified criteria, called weighted criteria, are suggested by combining the common criteria. In this study, the performances of the criteria available in the literature are compared by using both simulated and real-world datasets. We used three different exchange rate time series, four simulated time series with different structures and three well-known real-world datasets. The results show that the performances of the unweighted criteria vary depending on the data structure. However, the weighted criteria have performances as good as the popular criteria or better.

Keywords: Harmonic Regression; Periodograms; Consumer Price Index; Food Inflation; Turkey; Gaussian Distribution; Europe Union; GDP; Panel Data; Spatial Regression; Measurement Errors; Nonlinear Time Series; Chaotic Time Series; Weibull Distribution; Location Parameters; Fiducial Approach; Hypothesis Testing; Green Swan; Financial Stability; Annex II Countries; Financial Time Series; Kernels; Stock Index; Machine Learning; Statistical Learning; Optimization; WSAR Algorithm; Deep Neural Networks; Phyton; Parameter Estimation; COVID-19; Clustering Analyses; Artificial Neural Networks; Performance Criteria; Time Series Forecasting; Statistical Inference (search for similar items in EconPapers)
JEL-codes: C1 C4 C5 C6 C63 (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.worldscientific.com/doi/pdf/10.1142/9781800611757_0012 (application/pdf)
https://www.worldscientific.com/doi/abs/10.1142/9781800611757_0012 (text/html)
Ebook Access is available upon purchase.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:wschap:9781800611757_0012

Ordering information: This item can be ordered from

Access Statistics for this chapter

More chapters in World Scientific Book Chapters from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().