with a single summation unit, denoted by the symbol Σ . The collective outputs of these
modules constitute the input to the second processing layer consisting of J output units
that perform the flow prediction by applying some sort of the Bradley-Terry-Luce
model and enforcing satisfactorily the conservation rule of interaction from the
viewpoint of origins [destinations]4.

Figure 1: Architecture of the Product Unit Neural Spatial Interaction Model: The
Singly Constrained Case
The first layer of network parameters includes 2JH connection weights, so that
1 w ( j ^( j-1) H +1,2 j -1’ ..., j ^( j-1) H+h ,2 j-1’ "ɔ j PjH ,2 j-1, j P( j -1) H +1,2 j ’ ''" j P( j -1) H+h ,2 j ’ ''" j PjH ,2 j )
(10)
while the second layer contains JH weights:
2 w ( j ^( j-1) H +1’ ..., j ^( j-1) H+h’ ..., j ^ jH )
(11)
We have incorporated the basic trick of weight sharing into our network design to
reduce model complexity. Weight sharing involves forcing the set of connection
weights to be identical across the Jmodules. Thus, w = ( 1 w, 2 w) is a (3H)-dimensional
11
More intriguing information
1. What should educational research do, and how should it do it? A response to “Will a clinical approach make educational research more relevant to practice” by Jacquelien Bulterman-Bos2. The name is absent
3. Response speeds of direct and securitized real estate to shocks in the fundamentals
4. The name is absent
5. MANAGEMENT PRACTICES ON VIRGINIA DAIRY FARMS
6. Towards a Mirror System for the Development of Socially-Mediated Skills
7. ARE VOLATILITY EXPECTATIONS CHARACTERIZED BY REGIME SHIFTS? EVIDENCE FROM IMPLIED VOLATILITY INDICES
8. Improvement of Access to Data Sets from the Official Statistics
9. DETERMINANTS OF FOOD AWAY FROM HOME AMONG AFRICAN-AMERICANS
10. The name is absent