Mixture of Experts and Local-Global Neural Networks

- In this paper we investigate mixture of experts problems in the context of Local-Global Neural Networks. This type of architecture was originaly conceived for functional approximation and interpolation problems. Numerical experiments are presented, showing quite nice solutions. Because of its local characteristics, this type of approach brings the advantage of improving interpretability.

• Type: Conference
• Year: 2003
• Where: ESANN
• Authors: Mayte Suárez-Fariñas, Carlos Eduardo Pedreira
• Keywords: ESANN 2003, ESANN 2007, Experts Problems, Functional Approximation, Local-Global Neural Networks