Pattern Analysis & Applications

, Volume 5, Issue 2, pp 113–120

A Hybrid Projection-based and Radial Basis Function Architecture: Initial Values and Global Optimisation

  • S. Cohen
  • N. Intrator

DOI: 10.1007/s100440200010

Cite this article as:
Cohen, S. & Intrator, N. Pattern Anal Appl (2002) 5: 113. doi:10.1007/s100440200010


We introduce a mechanism for constructing and training a hybrid architecture of projection-based units and radial basis functions. In particular, we introduce an optimisation scheme which includes several steps and assures a convergence to a useful solution. During network architecture construction and training, it is determined whether a unit should be removed or replaced. The resulting architecture often has a smaller number of units compared with competing architectures. A specific overfitting resulting from shrinkage of the RBF radii is addressed by introducing a penalty on small radii. Classification and regression results are demonstrated on various benchmark data sets and compared with several variants of RBF networks [1,2]. A striking performance improvement is achieved on the vowel data set [3].

Key words: Clustering; Hybrid network architecture; Projection units; RBF units; Regularisation; SMLP 

Copyright information

© Springer-Verlag London Limited 2002

Authors and Affiliations

  • S. Cohen
    • 1
  • N. Intrator
    • 1
  1. 1.School of Computer Science, Tel-Aviv University, Ramat Aviv, IsraelIL

Personalised recommendations