The ensemble approach to neural-network learning and generalization

B Igelnik; Y H Pao; S R LeClair; C Y Shen

doi:10.1109/72.737490

The ensemble approach to neural-network learning and generalization

IEEE Trans Neural Netw. 1999;10(1):19-30. doi: 10.1109/72.737490.

Authors

B Igelnik¹, Y H Pao, S R LeClair, C Y Shen

Affiliation

¹ Case Western Reserve University, Cleveland, OH 44106, USA.

PMID: 18252500
DOI: 10.1109/72.737490

Abstract

In this paper a new method is suggested for learning and generalization with a general one-hidden layer feedforward neural network. This scheme encompasses the use of a linear combination of heterogeneous nodes having randomly prescribed parameter values. The learning of the parameters is realized through adaptive stochastic optimization using a generalization data set. The learning of the linear coefficients in the linear combination of nodes is achieved with a linear regression method using data from the training set. One node is learned at a time. The method allows for choosing the proper number of net nodes, and is computationally efficient. The method was tested on mathematical examples and real problems from materials science and technology.