Constructive and robust combination of perceptrons

Proceedings - International Conference on Pattern Recognition

Volumn 4, Issue , 1996, Pages 195-199

  Eigenmann, Robert ^a   Nossek, Josef A ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

Clustering; Constriictive Algorithm; Decision Boundaries; Internal Representation; Multi Layer Perceptron; Robustness

Indexed keywords

COMPLEX NETWORKS; FEEDFORWARD NEURAL NETWORKS; ITERATIVE METHODS; NETWORK LAYERS; PATTERN RECOGNITION; ROBUSTNESS (CONTROL SYSTEMS);

CLUSTERING; CONSTRUCTIVE TRAINING; DECISION BOUNDARY; GENERALIZATION PROPERTIES; HAND-WRITTEN CHARACTERS; INTERNAL REPRESENTATION; MULTI LAYER PERCEPTRON; TRAINING ERRORS;

CLUSTERING ALGORITHMS;

EID: 84898817676     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.1996.547260     Document Type: Conference Paper

References (12)

1. S . E. Fahlman and C. Lebiere. The cascade correlation learning architecture. Technical Report CMU-CS-90-100, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, Aug. 1991.
2. G. J. Gibson and C. E N. Cowan. On the decision regions of multilayer perceptrons. Proc. of the IEEE, 78(10): 1590-1594, oct 1990.
3. R. C. Gonzalez and P. Wintz. Digital Image Processing. Addison Wesley, Reading, MA, 1987.
4. M. Mezard and J.-P. Nadal. Learning in feedforward layered networks: The tiling algorithm. J. Phys. A: Math. Gen., 22:1291-2203.1989.
5. M. L. Minksy and S. Papert. Perceptrotis. M.I.T.-Press, Cambridge, expanded edition, 1988.
6. P. Nachbar. Entwurf robuster neirronaler Netze. PhD thesis, Technical University Munich, Institute for Network Theory and Circuit Design, 1994.
7. P. Nachbar, J. Strobl, and J. Nossek. The generalized adatron algorithm. In Intertiatiotial Symposium oti Circuits and Svstems, volume 4, pages 2152-2156. IEEE, 1993.
8. The state-of-the-art in OCR is subject of NIST/Census conference. Intelligence, 9(6): 1-5, 1992.
9. J. Nossek, P. Nachbar, and A. Schuler. Comparison of Algorithms for Feedforward Multilayer Neural Nets. ISCAS, Atlanta, to be published, 1996.
10. F. Rosenblatt. Principles of Neurodytiamics: Perceptrotis and the Theory of Brain Mechanism. Sparta, Washington, D.C., 1961.
11. W. Utschick and J. Nossek. Bayesian Adaptation of Hidden Layersin Boolean Feedforward NeuralNetworks. 1996.13th International Conference on Pattern Recognition, Vienna.
12. B. Widrow and M. Lehr. 30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation. Proc. ofthe IEEE, 78(9) 1415-1441, 1990.