论文信息 - Input partitioning to mixture of experts

Input partitioning to mixture of experts

Given a supervised learning context, the mixture of experts approach uses several neural networks in parallel to provide a modular solution to the overall problem.. Under the mixtures of experts architecture a method for 'designing' the number of experts and assigning local 'regions' of the input space to individual experts is investigated. Classification performance and transparency of the scheme is found to be significantly better than that using a standard mixtures of experts.

[1] Michael I. Jordan,et al. Modular and hierarchical learning systems , 1998 .

[2] Teuvo Kohonen,et al. The self-organizing map , 1990 .

[3] Rajesh N. Davé,et al. Robust clustering methods: a unified view , 1997, IEEE Trans. Fuzzy Syst..

[4] Esa Alhoniemi,et al. Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[5] Bernd Fritzke,et al. Kohonen Feature Maps and Growing Cell Structures - a Performance Comparison , 1992, NIPS.

[6] Stephen L. Chiu,et al. Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..

[7] Michael I. Jordan,et al. Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[8] Juyang Weng,et al. Using Discriminant Eigenfeatures for Image Retrieval , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9] Michael I. Jordan,et al. Hierarchical Mixtures of Experts and the EM Algorithm , 1994 .