Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


Structural Adaptation and Generalization in Supervised Feedforward Networks. J. Ghosh and K. Tumer. Journal of Artificial Neural Networks, 1(4):431–458, 1994.

Abstract

This work explores diverse techniques for improving the generalization ability of supervised feed-forward neural networks via structural adaptation, and introduces a new network structure with sparse connectivity. Pruning methods which start from a large network and proceed in trimming it until a satisfactory solution is reached, are studied first. Then, construction methods, which build a network from a simple initial configuration, are presented. A survey of related results from the disciplines of function approximation theory, nonparametric statistical inference and estimation theory leads to methods for principled architecture selection and estimation of prediction error. A network based on sparse connectivity is proposed as an alternative approach to adaptive networks. The generalization ability of this network is improved by partly decoupling the outputs. We perform numerical simulations and provide comparative results for both classification and regression problems to show the generalization abilities of the sparse network.

Download

[PDF]7.2MB  

BibTeX Entry

@article{tumer-ghosh_jann94,
        author={J. Ghosh and K. Tumer},
        title="Structural Adaptation and Generalization in Supervised Feedforward Networks",
        journal={Journal of Artificial Neural Networks},
        volume={1},
        number={4},
	pages={431-458},
	abstract={This work explores diverse techniques for improving the generalization ability of supervised feed-forward neural networks via structural adaptation, and introduces a new network structure with sparse connectivity. Pruning methods which start from a large network and proceed in trimming it until a satisfactory solution is reached, are studied first. Then, construction methods, which build a network from a simple initial configuration, are presented. A survey of related results from the disciplines of function approximation theory, nonparametric statistical inference and estimation theory leads to methods for principled architecture selection and estimation of prediction error. A network based on sparse connectivity is proposed as an alternative approach to adaptive networks. The generalization ability of this network is improved by partly decoupling the outputs. We perform numerical simulations and provide comparative results for both classification and regression problems to show the generalization abilities of the sparse network.},
	bib2html_pubtype = {Journal Articles},
	bib2html_rescat = {Other Topics, Classifier Ensembles},
        year={1994}
}

Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 26, 2018 19:10:42