Download Now Free registration required
In this paper, the authors present an extended form of the radial basis function network called temporal-radial basis function network. This extended network is used in decision rules and classification in spatio-temporal domain applications like speech recognition, economic fluctuations, seismic measurements and robotics applications. They found that such a network complies, with a relative ease, to constraints such as capacity of universal approximation, sensibility of node, local generalisation in receptive field, etc. For an optimal solution based on a probabilistic approach with a minimum of complexity, they developed two temporal radial basis function models. Application to the problem of Mackey-Glass time series, it has revealed that temporal radial basis function models are very promising, compared to traditional networks.
- Format: PDF
- Size: 1292.6 KB