Self-Organizing Neural Network for Diagnosis
The paper describes an approach to diagnostic applications that uses a selforganizing classifier, capable of performing incremental learning and of dealing with noisy data, and allows to estimate the distance from pathological regions and the time-to-failure.
KeywordsWeight Vector Hide Neuron Decision Boundary Category Learning Incremental Learning
Unable to display preview. Download preview PDF.
- Le Cun, Y., Denker, J.S., and S.A. Solla (1990) Optimal brain damage. In “Advances in neural information processing systems” (D.S. Touretzky ed.), 2, Morgan Kaufman, 598–605.Google Scholar
- Alpaydin, E. (1991) Grow and learn: an incremental method for category learning. International Neural Network Conference, Paris, France.Google Scholar
- Fritzke, B. (1991) Let it grow. Self-organizing feature maps with problem dependent cell structure. In “Artificial Neural Networks” (T. Kohonen, K. Makisara, O. Simula, and J. Kangas, Eds.), 1, 403–408, North Holland, Amsterdam.Google Scholar
- Morasso, P., Pagliano, S., and A. Pareto (1992) Neural models for handwriting recognition. In “Proceedings of the Second International Workshop on Frontiers in Handwriting Recognition” (S. Impedovo and J.C. Simon, Editors), Elsevier, Amsterdam.Google Scholar
- Kohonen, T. (1989) Self-Organisation and Associative Memory (3rd ed.). Springer-Verlag Series in Information Sciences, Berlin.Google Scholar
- Martinetz, T. and K. Schulten (1991) A “neural gas” network learns topologies. In “Artificial Neural Networks” (T. Kohonen, K. Makisara, O. Simula, and J. Kangas, Eds.), 1, 397–402, North Holland, Amsterdam.Google Scholar