In this paper we show how we can compute in a deterministic way the decomposition of a multivariate rational function with a recombination strategy. The key point of our recombinat...
The choice of transfer functions may strongly influence complexity and performance of neural networks used in classification and approximation tasks. A taxonomy of activation an...
Abstract. We present basic concepts and an outlook on current approaches and techniques of personal learning environments to point out their demands, focussing on recommendations i...
Uwe Kirschenmann, Maren Scheffel, Martin Friedrich...
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
There is a close relationship between harmonic functions { which have recently been proposed for path planning { and hitting probabilities for random processes. The hitting probab...