Computational Neural Networks - A New Paradigm for Spatial Analysis

Environment and Planning A, Vol. 30, No. 10, pp. 1873-1892, 2009

Posted: 20 Dec 2009

See all articles by Manfred M. Fischer

Manfred M. Fischer

Vienna University of Economics and Business - Institute for Economic Geography and GIScience, Department of Socioeconomics

Date Written: December 15, 2009

Abstract

In this paper a systematic introduction to computational neural network models is given in order to help spatial analysts learn about this exciting new field. The power of computational neural networks viz-à-viz conventional modelling is illustrated for an application field with noisy data of limited record length: spatial interaction modelling of telecommunication data in Austria. The computational appeal of neural networks for solving some fundamental spatial analysis problems is summarized and a definition of computational neural network models in mathematical terms is given. Three definitional components of a computational neural network - properties of the processing elements, network topology and learning - are discussed and a taxonomy of computational neural networks is presented, breaking neural networks down according to the topology and type of interconnections and the learning paradigm adopted. The attractiveness of computational neural network models compared with the conventional modelling approach of the gravity type for spatial interaction modelling is illustrated before some conclusions and an outlook are given.

Suggested Citation

Fischer, Manfred M., Computational Neural Networks - A New Paradigm for Spatial Analysis (December 15, 2009). Environment and Planning A, Vol. 30, No. 10, pp. 1873-1892, 2009, Available at SSRN: https://ssrn.com/abstract=1523784

Manfred M. Fischer (Contact Author)

Vienna University of Economics and Business - Institute for Economic Geography and GIScience, Department of Socioeconomics ( email )

Welthandelsplatz 1, D4
Vienna, 1020
Austria

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
539
PlumX Metrics