Neural Network Modelling of Constrained Spatial Interaction Flows



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. The name is absent
2. The name is absent
3. Who’s afraid of critical race theory in education? a reply to Mike Cole’s ‘The color-line and the class struggle’
4. Income Mobility of Owners of Small Businesses when Boundaries between Occupations are Vague
5. Luce Irigaray and divine matter
6. Synthesis and biological activity of α-galactosyl ceramide KRN7000 and galactosyl (α1→2) galactosyl ceramide
7. NVESTIGATING LEXICAL ACQUISITION PATTERNS: CONTEXT AND COGNITION
8. Delayed Manifestation of T ransurethral Syndrome as a Complication of T ransurethral Prostatic Resection
9. The name is absent
10. Weather Forecasting for Weather Derivatives