Neural Network Modelling of Constrained Spatial Interaction Flows



they may be of little practical value in situations where the set of row totals or the set of
column totals of the spatial interaction matrix
TIxJ is known a priori. For such
situations, the families of production constrained and attraction-constrained models of
the gravity type had been developed.

The question arises how to build neural network models for the case of singly
constrained spatial interactions. Following Openshaw (1998) constrained spatial
interaction modelling may be viewed as consisting of two parts:

The prediction of flows, and

the imposing of accounting constraints.

These two parts can be treated separately or simultaneously. The question that follows
is whether to embed the constraint-handling mechanism within the neural network
approach [
one-stage modelling approach] or whether to estimate the unconstrained
neural spatial interaction model first and then to apply the accounting constraints
subsequently [
two-stage modelling approach]. The one-stage modelling approach is
harder, requiring major changes to the model structure, while the two-stage approach is
much simpler [for an application see Mozolin, Thill and Usery (2000)].

3 The One-Stage Modelling Approach: The Modular Product Unit Network
Model

3.1 Why Product rather than Summation Unit Networks?

Classical neural spatial interaction models, such as Ω (x, w) and ΩL (x, w), are
constructed using a single hidden layer of summation units. In these networks each
input to the hidden node is multiplied by a weight and then summed. A non-linear
transfer function, such as the logistic function, is used to squash the sum. Neural
network approximation theory has shown the attractivity of such summation networks
for unconstrained spatial interaction contexts. But these networks require a larger
number of hidden summation units when approximating complex functions
g , such as
those for mapping constrained interaction phenomena.



More intriguing information

1. BILL 187 - THE AGRICULTURAL EMPLOYEES PROTECTION ACT: A SPECIAL REPORT
2. FDI Implications of Recent European Court of Justice Decision on Corporation Tax Matters
3. Developing vocational practice in the jewelry sector through the incubation of a new ‘project-object’
4. THE ANDEAN PRICE BAND SYSTEM: EFFECTS ON PRICES, PROTECTION AND PRODUCER WELFARE
5. Ex post analysis of the regional impacts of major infrastructure: the Channel Tunnel 10 years on.
6. The name is absent
7. The purpose of this paper is to report on the 2008 inaugural Equal Opportunities Conference held at the University of East Anglia, Norwich
8. Educational Inequalities Among School Leavers in Ireland 1979-1994
9. Macroeconomic Interdependence in a Two-Country DSGE Model under Diverging Interest-Rate Rules
10. Implementation of Rule Based Algorithm for Sandhi-Vicheda Of Compound Hindi Words
11. Firm Closure, Financial Losses and the Consequences for an Entrepreneurial Restart
12. Endogenous Heterogeneity in Strategic Models: Symmetry-breaking via Strategic Substitutes and Nonconcavities
13. Income Growth and Mobility of Rural Households in Kenya: Role of Education and Historical Patterns in Poverty Reduction
14. The name is absent
15. Public-Private Partnerships in Urban Development in the United States
16. Knowledge, Innovation and Agglomeration - regionalized multiple indicators and evidence from Brazil
17. Comparison of Optimal Control Solutions in a Labor Market Model
18. Foreword: Special Issue on Invasive Species
19. Optimal Rent Extraction in Pre-Industrial England and France – Default Risk and Monitoring Costs
20. CAPACITAÇÃO GERENCIAL DE AGRICULTORES FAMILIARES: UMA PROPOSTA METODOLÓGICA DE EXTENSÃO RURAL