In this paper a novel modular product unit neural network architecture is presented to model singly constrained spatial interaction flows. The efficacy of the model approach is demonstrated for the origin constrained case of spatial interaction using Austrian interregional telecommunication...

This paper presents a methodology for neural spatial interaction modelling. Particular emphasis is laid on design, estimation and performance issues in both cases, unconstrained and singly constrained spatial interaction. Families of classical neural network models, but also less classical ones...

Parameter estimation is one of the central issues in neural spatial interaction modelling. Current practice is dominated by gradient based local minimization techniques. They find local minima efficiently and work best in unimodal minimization problems, but can get trapped in multimodal...

Fundamental to regional science is the subject of spatial interaction. GeoComputation - a new research paradigm that represents the convergence of the disciplines of computer science, geographic information science, mathematics and statistics - has brought many scholars back to spatial...

The focus in this paper is on knowledge spillovers between high-technology firms in Europe, as captured by patent citations. High-technology is defined to include the ISIC-sectors aerospace (ISIC 3845), electronics-telecommunication (ISIC 3832), computers and office equipment (ISIC 3825), and...

The focus of this paper is on pre-competitive R&D cooperation across Europe, as captured by R&D joint ventures funded by the European Commission in the time period 2002-2006, within the 5th Framework Program. The cooperations in this Framework Program give rise to a collaborative network, with...