Bayesian adaptation of hidden layers in Boolean feedforward neural networks

Proceedings - International Conference on Pattern Recognition

Volumn 4, Issue , 1996, Pages 229-233

  Utschick, Wolfgang ^a   Nossek, Josef A ^a  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

Author keywords

Bayesian Adaptation; Boolean Function; Classification; Discrete Probability Space; Handwritten Characters; Indicator Function; Internal Representation; Multilayer Perceptron

Indexed keywords

CLASSIFICATION (OF INFORMATION); FEEDFORWARD NEURAL NETWORKS; INPUT OUTPUT PROGRAMS; PATTERN RECOGNITION;

BAYESIAN ADAPTATION; HAND-WRITTEN CHARACTERS; INDICATOR FUNCTIONS; INTERNAL REPRESENTATION; MULTI LAYER PERCEPTRON; PROBABILITY SPACES;

BOOLEAN FUNCTIONS;

EID: 11744304420     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.1996.547421     Document Type: Conference Paper

References (21)

1. Learning internal representations by error propagation, . In D. Rumelhart and J. McClelland, editors, Parallel Distributed Processing, volume 1, chapter 8. MIT Press, Cambridge, MA, 1986.
2. M. Anthony and N. Biggs. Computational Learning Theory for Artificial Neural Networks. In J. G. Taylor, editor, Mathematical Approaches to Neural Networks, pages 25-62. Elsevier Science Publishers B.V., 1993.
3. E. B. Baum. On the Capabilities of Multilayer Perceptrons. J. of Complexity, 4:193-215, 1988.
4. P. Billingsley. Probability and Measure. Wiley. 1979.
5. T. M. Cover. Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition. IEEE Trans. on Elect. Comp., 14:326-334, 1965.
6. R. Eigenmann and J. Nossek. Constructive and Robust Combination of Perceptrons. 13th International Conference on Pattern Recognition, Vienna, 1996.
7. K. Fukunaga. Introduction to Statistical Pattern Recognition. Academic Press, 1972.
8. J. Ghosh and K. Tumer. Structural Adaptation and Generalization in Supervised Feed-Forward Networks. Technical report, The University of Texas at Austin, Department of Electrical and Computer Engineering, 1995.
9. G. Gibson and C. Cowan. On the Decision Regions of Multilayer Perceptrons. IEEE Proc., 78( 10): 1590-1594, 1990.
10. D. Hush and B. Home. Progress in Supervised Neural Networks. IEEE Signal Processing Magazine, pages 8-39, January 1993.
11. M. Minsky and S. Papert. Perceptrons. MIT Press, Cambridge, 1969.
12. S . Muroga. Threshold Logic and Its Applications. Wiley-Interscience, 1971.
13. P. Nachbar. Entwurj-robuster neumnaler Netze. PhD thesis, Technical University Munich, Institute for Network Theory and Circuit Design, 1994.
14. P. Nachbar, J. Strobl, and J. Nossek. The generalized adatron algorithm. In International Symposium on Circuits and Systems, volume 4, pages 2152-2156. IEEE, 1993.
15. The state-of-the-art in OCR is subject of NIST conference. Intelligence, 9(6): 1-5, 1992.
16. J. Nossek, P. Nachbar, and A. Schuler. Comparison of Algorithms for Feedforward Multilayer Neural Nets. ISCAS. Atlanta, to be published, 1996.
17. W. Utschick. How To Improve Multi Layer Perceptrons Using Statistics. Technical Report TUM-LNS-TR-95-4, Technical University Munich, 1995.
18. H. Veit. Automatischer Design von Codes fur die Mustererkennung von Mehrfachklassen mit neuronalen Netzen, to be published. Master's thesis, Technical University Munich, Institute for Network Theory and Circuit Design, 1996.
19. B. Widrow and M. Lehr. 30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation. IEEE Proc.78(9):1415-1441, 1990.
20. B. Widrow, R. Winter, and R. Baxter. Layered Neural Nets for Pattern Recognition. IEEE Trans. on Acoustics, Speech, and Signal Processing. 36(7): 1109-1118, 1988.
21. T. Young and T. Calvert, Classijcation, Estimation And Pattern Recognition. American Elsevier Publishing Co. Inc. 1974.