Skip to Main content Skip to Navigation
Journal articles

A new multilayer perceptron pruning algorithm for classification and regression applications

Abstract : Optimizing the structure of neural networks remains a hard task. If too small, the architecture does not allow for proper learning from the data, whereas if the structure is too large, learning leads to the well-known overfitting problem. This paper considers this issue, and proposes a new pruning approach to determine the optimal structure. Our algorithm is based on variance sensitivity analysis, and prunes the different types of unit (hidden neurons, inputs, and weights) sequentially. The stop criterion is based on a performance evaluation of the network results from both the learning and validation datasets. Four variants of this algorithm are proposed. These variants use two different estimators of the variance. They are tested and compared with four classical algorithms on three classification and three regression problems. The results show that the proposed algorithms outperform the classical approaches in terms of both computational time and accuracy.
Document type :
Journal articles
Complete list of metadata

Cited literature [84 references]  Display  Hide  Download
Contributor : Philippe Thomas Connect in order to contact the contributor
Submitted on : Tuesday, November 25, 2014 - 9:44:26 AM
Last modification on : Saturday, October 16, 2021 - 11:14:12 AM
Long-term archiving on: : Thursday, February 26, 2015 - 10:50:34 AM


NPL Thomas Suhner 2014 HAL.pdf
Files produced by the author(s)




Philippe Thomas, Marie-Christine Suhner. A new multilayer perceptron pruning algorithm for classification and regression applications. Neural Processing Letters, Springer Verlag, 2015, 42 (2), pp.437-458. ⟨10.1007/s11063-014-9366-5⟩. ⟨hal-01086842⟩



Record views


Files downloads