Hybrid Learning of Regularization Neural Networks
Regularization theory presents a sound framework to solving supervised learning problems. However, the regularization networks have a large size corresponding to the size of training data. In this work we study a relationship between network complexity, i.e. number of hidden units, and approximation and generalization ability. We propose an incremental hybrid learning algorithm that produces smaller networks with performance similar to original regularization networks.
KeywordsHybrid Algorithm Generalization Ability Hide Unit Small Network Reproduce Kernel Hilbert Space
Unable to display preview. Download preview PDF.
- 2.Poggio, T., Girosi, F.: A theory of networks for approximation and learning. Technical report, Cambridge, MA, USA (1989); A. I. Memo No. 1140, C.B.I.P. Paper No. 31Google Scholar
- 8.Prechelt, L.: PROBEN1 – a set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report 21/94, Universitaet Karlsruhe (November 1994)Google Scholar
- 9.Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 9(87), 1423–1447 (1999)Google Scholar
- 10.Stanley, K.O., D’Ambrosio, D., Gauci, J.: A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life 15(2) (2009)Google Scholar