Optimal Linear Combinations of Neural Networks

DMCA

Optimal Linear Combinations of Neural Networks (1994)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Sherif Hashem

Venue:	NEURAL NETWORKS
Citations:	155 - 2 self

BibTeX

@ARTICLE{Hashem94optimallinear,
    author = {Sherif Hashem},
    title = {Optimal Linear Combinations of Neural Networks},
    journal = {NEURAL NETWORKS},
    year = {1994},
    volume = {10},
    number = {4},
    pages = {599--614}
}

OpenURL

Abstract

Neural network (NN)-based modeling often involves trying multiple networks with different architectures and training parameters in order to achieve acceptable model accuracy. Typically, one of the trained NNs is chosen as best, while the rest are discarded. Hashem and Schmeiser [25] proposed using optimal linear combinations of a number of trained neural networks instead of using a single best network. Combining the trained networks may help integrate the knowledge acquired by the component networks and thus improve model accuracy. In this paper, we discuss and extend the idea of optimal linear combinations (OLCs) of neural networks and derive closedform expressions for four cases of OLCs. We present two algorithms for selecting the component networks for the combination to improve the generalization ability of OLCs. Our experimental results demonstrate significant improvements in model accuracy as a result of using OLCs, as compared to the best network.

Keyphrases

optimal linear combination neural network model accuracy component network multiple network trained network single best network derive closedform expression trained neural network acceptable model accuracy experimental result demonstrate significant improvement different architecture trained nns generalization ability

DMCA