Hierarchies of Adaptive Experts
暂无分享,去创建一个
In this paper we present a neural network architecture that discovers a recursive decomposition of its input space. Based on a generalization of the modular architecture of Jacobs, Jordan, Nowlan, and Hinton (1991), the architecture uses competition among networks to recursively split the input space into nested regions and to learn separate associative mappings within each region. The learning algorithm is shown to perform gradient ascent in a log likelihood function that captures the architecture's hierarchical structure.
[1] R. Preston. North American Trees , 1908, Botanical Gazette.
[2] John Scott Bridle,et al. Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.
[3] J. Freidman,et al. Multivariate adaptive regression splines , 1991 .
[4] Geoffrey E. Hinton,et al. Adaptive Mixtures of Local Experts , 1991, Neural Computation.