Evaluation of Adaptive Mixtures of Competing Experts

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Private Federated Learning with Domain Adaptation (2019, methodology): “Each user combines the output of the general and private models using a mixture of experts (MoE) (19; 21) to make their ﬁnal predictions.”
Model learning for robot control: a survey (2011, background): “An example of such hybrid approaches is the mixture of experts (Jacobs et al. 1991; Nowlan and Hinton 1991).”
Decision templates for multiple classifier fusion: an experimental comparison (2001, background): “• combination of multiple classifiers ([1, 2, 3, 4, 5]); • classifier fusion ([6, 7, 8, 9, 10]); • mixture of experts ([11, 12, 13, 14]); • committees of neural networks ([15, 16]); • consensus aggregation ([17, 18, 19]); • voting pool of classifiers ([20]); • dynamic classifier selection ([3]); ∗Re”
Bias/Variance Analyses of Mixtures-of-Experts Architectures (1997, background): “From an empirical viewpoint, they have been shown to be capable of comparatively fast learning and good generalization on a wide variety of regression and classification tasks (Jacobs et al. 1991; Jordan and Jacobs 1994; Nowlan and Hinton 1991; Waterhouse and Robinson 1994).”
Twenty Years of Mixture of Experts (2012, result): “In comparison to NNs, Nowlan and Hinton [112] found ME to be better at fitting the training data.”