Neural Network Modelling of Constrained Spatial Interaction Flows



process stabilises and the changes in validation error become smaller. According to our
termination criterion, training is stopped after 18,841 iterations. At this stopping point,
P, the model is used for testing (prediction).

(a) Training Set

0       5      10      15     20      25     30

Training Time in Terms of Iterations [in 1000]


(b) Validation Set

0       5      10      15     20     25     30

Training Time in Terms of Iterations [in 1000]


(c) Testing Set

0       5      10      15     20      25     30

Training Time in Terms of Iterations [in 1000]

Figure 3: Training, Validation and Testing Set Curves as a Function of Training Time
(the vertical line
P indicates the stopping point): The Modular Product Unit
Neural Network for Origin Constrained Spatial Interactions


(d) Annealing Schedule

0       5      10      15     20     25     30

Training Time in Terms of Iterations [in 1000]


5.4 The Benchmark Models

The first benchmark model is the standard origin constrained gravity model, a special
case of the generic interaction model of the gravity type (see Equation (5))13:

(34)


τ grav = b r sd -p
ij                   ( i )     i j ij

with

26



More intriguing information

1. Globalization, Redistribution, and the Composition of Public Education Expenditures
2. HOW WILL PRODUCTION, MARKETING, AND CONSUMPTION BE COORDINATED? FROM A FARM ORGANIZATION VIEWPOINT
3. The name is absent
4. Food Prices and Overweight Patterns in Italy
5. Growth and Technological Leadership in US Industries: A Spatial Econometric Analysis at the State Level, 1963-1997
6. The name is absent
7. Infrastructure Investment in Network Industries: The Role of Incentive Regulation and Regulatory Independence
8. ENVIRONMENTAL POLICY: THE LEGISLATIVE AND REGULATORY AGENDA
9. On the Integration of Digital Technologies into Mathematics Classrooms
10. The name is absent