Performance Evaluation of Recurrent RBF Network in Nearest Neighbor Classification
Superposition of radial basis functions centered at given prototype patterns constitutes one of the most suitable energy forms for gradient systems that perform nearest neighbor classification with real-valued static prototypes. It has been shown in  that a continuous-time dynamical neural network model, employing a radial basis function and a sigmoid multi-layer perceptron sub-networks, is capable of maximizing such an energy form locally, thus performing almost perfectly nearest neighbor classification, when initiated by a distorted pattern. This paper reviews the proposed design procedure and presents the results of the intensive experimentation of the classifier on random prototypes.
KeywordsRadial Basis Function Associative Memory Pattern Space Unit Hypercube Radial Basis Function Network Model
Unable to display preview. Download preview PDF.
- 1.Muezzinoglu, M.K., Zurada, J.M.: RBF-based neurodynamic nearest neighbor classification in real pattern space (submitted, 2005)Google Scholar
- 2.Garey, M.R., Johnson, D.S.: Computers and Interactability. W.H. Freeman, New York (1979)Google Scholar
- 11.Khalil, H.K.: Nonlinear Systems, 3rd edn. Prentice-Hall, Englewood Cliffs (2001)Google Scholar
- 12.Zurada, J.M.: Introduction to Artificial Neural Systems. West, St. Paul (1992)Google Scholar
- 13.Michel, A.N., Liu, D.: Qualitative Analysis and Sythesis of Recurrent Neural Networks. Marcel Dekker, New York (2002)Google Scholar