Overcome neural limitations for real world applications by providing confidence values for network prediction

ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings

Volumn 2, Issue , 1999, Pages 520-525

  Tagscherer, Michacl ^a   Kindermann, Lars ^a   Lewandowski, Achim ^a   Protzel, Peter ^b  

^a Bayerisches Forschungszentrum fur wissensbasierte Systeme FORWISS   (Germany)

^b CHEMNITZ UNIVERSITY OF TECHNOLOGY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

FORECASTING; HYBRID SYSTEMS; RADIAL BASIS FUNCTION NETWORKS;

CONFIDENCE VALUES; CONTINUOUS LEARNING; INCREMENTAL CONSTRUCTION; INDUSTRIAL CONTROLS; NETWORK PREDICTION; STRONG INTERACTION; SYSTEM PREDICTION; TARGET FUNCTIONS;

NETWORK LAYERS;

EID: 34147100447     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICONIP.1999.845648     Document Type: Conference Paper

References (7)

1. Martinetz T, Protzel P., Gramckow O, and Sorgel G. Neural network control for steel rolling mills, in B. Kappen and S. Giele, editors, Neural Networks: artificial intelligence and industrial application, Berlin, 1995, Springcr-Verlag.
2. Carpenter, G., Grossberg, S.: A massively parallel architecture for a selforganizing neural pattern recognition machine. Computer Vision, Graphics and Image Processing, pp. 54-115., 1987
3. Poggio, T., Girosi, F.: Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks. Science 247, pp. 978-982, 1990.
4. Kohonen, T.: Self-organized formation of topological^ correct feature maps. Biological Cybernetics, 43:59-69, 1982.
5. Hecht-Nielsen, R.: Counterpropagation networks. Proc. of the IEEE First International Conference on Neural Networks, Vol. 2, pp. 19-32, San Diego, CA 1987.
6. Tagsche re r, M.: ICE-an I ncre men tal Hybrid System for Continuous Learning, Proceedings of the 8th Internationa] Conference on Artificial Neural Networks (ICANN'98), Skovde, Schweden, Sep 1998, pp. 597-602.
7. Bcrthold, M., Diamond J.; Boosting the Performance of RBF Networks with Dynamic Decay Adjustment. Advances in Neural Information Processing Systems 7, Morgan Kaufmann Publishers, San Mateo, CA, 1994.