In this paper, evolution strategy is applied in order to improve the time series prediction accuracy of a Sugeno and Takagi type fuzzy inference system FIS. The presented approach...
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...
In this paper, approximation by linear combinations of an increasing number n of computational units with adjustable parameters (such as perceptrons and radial basis functions) is ...
A new class of data structures called "bumptrees" is described. These structures are useful for efficiently implementing a number of neural network related operations. A...