Reconsideration to pruning and regularization for complexity optimization in neural networks

Hyeyoung Park, Hyunjin Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The ultimate purpose of neural network design is to find an optimal network that can give good generalization performance with compact structure. To achieve this, it is necessary to control complexities of networks so as to avoid its overfitting to noisy learning data. The most popular methods for complexity control are the pruning method and the regularization method. Even though there have been many variations in the methods, the peculiar properties of each method compared to others has not been so clear. We reconsider the pruning strategy from a geometrical and statistical viewpoint, and show that the natural pruning method is in accordance with the geometrical and statistical intuition in choosing connections to be pruned. In addition, we also suggest that the regularization method should be used in combination with natural pruning in order to improve the optimization performance. We also show some experimental results supporting our suggestions.

Original languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publicationComputational Intelligence for the E-Age
EditorsKunihiko Fukushima, Lipo Wang, Jagath C. Rajapakse, Soo-Young Lee, Xin Yao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1649-1653
Number of pages5
ISBN (Electronic)9810475241, 9789810475246
DOIs
StatePublished - 2002
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: 18 Nov 200222 Nov 2002

Publication series

NameICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Volume4

Conference

Conference9th International Conference on Neural Information Processing, ICONIP 2002
Country/TerritorySingapore
CitySingapore
Period18/11/0222/11/02

Fingerprint

Dive into the research topics of 'Reconsideration to pruning and regularization for complexity optimization in neural networks'. Together they form a unique fingerprint.

Cite this