Multi-Layered Neural Networks with Learning of Output Functions
Lixin Ma, Hiromi Miyajima, Noritaka Shigei · 2006
Summary This paper proposes multi-layered neural networks with learning of output functions like RBF and fuzzy models. Various models that differ in the number of trained output functions are compared in two types of simulations: XOR problem and functional approximation. As a result it is shown that the proposed models are faster in learning time than the conventional one. Further, based on the simulation results, an effective heuristic model is proposed.