Neural Network Modelling of Constrained Spatial Interaction Flows



4 Training the Modular Product Unit Network Model
4.1 The Optimisation Problem

Having identified the model structure for singly constrained spatial interaction
prediction in the previous section, we can now follow section 2.2 to view network
training in an optimisation context and proceed by considering the parameter estimation
problem as least squares learning. The goal of least squares learning is to find
w* so
that the least square error function, say
Q, is minimized5:

min Q ( xu 1, yu 1, w ) ~ min      ( yu 1 - 1 l ( xu 1, w ))

(26)


ww

( xu 1, yu 1 ) Ш1

where M1 denotes the training set available consisting of observations, say
xu 1 (u = 1,..., U1 ) on the input variables together with observations, say
yu 1 (u = 1,..., U1 ), on corresponding target variables, the network model is to learn to
associate with
xu1 .

Q (xu 1, yu 1, w) is non-negative, continuously differentiable on the (3^)-dimensional
parameter space which is a finite dimensional closed bounded domain and, thus,
compact. The compactness of the parameter space is of great theoretical convenience. It
can be shown that
Q (xu 1, yu 1, w) assumes its value w* as the weight minimum under
certain conditions. But characteristically there exist many minima in real world
applications all of which satisfy

V Q ( xu 1, yu 1, w* ) = 0
where
NQ denotes the gradient of Q. The minimum for which the value of Q is
smallest is termed the global minimum while other minima are called local minima.
Unfortunately there is no guarantee about which kind of minimum is encountered.

(27)


The fraction of the parameter space that contains a solution depends on the capacity of
the network model [in an information theoretic sense] and the complexity of the

16



More intriguing information

1. The Veblen-Gerschenkron Effect of FDI in Mezzogiorno and East Germany
2. The name is absent
3. Skill and work experience in the European knowledge economy
4. Who runs the IFIs?
5. The name is absent
6. Structure and objectives of Austria's foreign direct investment in the four adjacent Central and Eastern European countries Hungary, the Czech Republic, Slovenia and Slovakia
7. Wage mobility, Job mobility and Spatial mobility in the Portuguese economy
8. The name is absent
9. Special and Differential Treatment in the WTO Agricultural Negotiations
10. The name is absent
11. The Evolution
12. Solidaristic Wage Bargaining
13. The name is absent
14. Searching Threshold Inflation for India
15. Concerns for Equity and the Optimal Co-Payments for Publicly Provided Health Care
16. FUTURE TRADE RESEARCH AREAS THAT MATTER TO DEVELOPING COUNTRY POLICYMAKERS
17. Banking Supervision in Integrated Financial Markets: Implications for the EU
18. Cyber-pharmacies and emerging concerns on marketing drugs Online
19. Improving the Impact of Market Reform on Agricultural Productivity in Africa: How Institutional Design Makes a Difference
20. New Evidence on the Puzzles. Results from Agnostic Identification on Monetary Policy and Exchange Rates.