Table of Contents

Handbook of Research Methods and Applications in Economic Geography

Handbook of Research Methods and Applications in Economic Geography

Handbooks of Research Methods and Applications series

Edited by Charlie Karlsson, Martin Andersson and Therese Norman

The main purpose of this Handbook is to provide overviews and assessments of the state-of-the-art regarding research methods, approaches and applications central to economic geography. The chapters are written by distinguished researchers from a variety of scholarly traditions and with a background in different academic disciplines including economics, economic, human and cultural geography, and economic history. The resulting handbook covers a broad spectrum of methodologies and approaches applicable in analyses pertaining to the geography of economic activities and economic outcomes.

Chapter 8: Neural networks: a class of flexible non-linear models for regression and classification

Manfred M. Fischer

Subjects: economics and finance, regional economics, geography, economic geography, research methods in geography, research methods, research methods in economics, research methods in geography, urban and regional studies, regional economics, research methods in urban and regional studies


Neural networks form a field of research that has enjoyed rapid expansion and increasing popularity in recent years. The exuberance of this growth has been accompanied by exaggerated claims concerning the technological potential of neural networks. In addition, a definite mystique perceived by those outside the field arises from the origins of neural networks in the study of natural neural systems, and in the associated metaphorical jargon in the field. Both the exaggerated claims and the mystique may have acted to lessen the amount of serious attention given to neural networks in economic geography and regional science. This chapter is intended as a convenient resource for those interested in a more fundamental view of the neural network modelling approach. The primary aim is to discuss some issues that are crucial for the design and understanding of neural network models, with a strong emphasis on their practical use for solving regression and classification problems.

You are not authenticated to view the full text of this chapter or article.

Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.

Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.

Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.

Further information