Nonlinear autoassociation is not equivalent to PCA

Neural Computation

Volumn 12, Issue 3, 2000, Pages 531-545

  Japkowicz, Nathalie ^a   Hanson, Stephen José ^b   Gluck, Mark A ^c  

^a DALHOUSIE UNIVERSITY   (Canada)

^b RUTGERS UNIVERSITY   (United States)

^c RUTGERS UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; NONLINEAR SYSTEM; NORMAL DISTRIBUTION; REPRODUCIBILITY; STATISTICAL MODEL;

LINEAR MODELS; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; NORMAL DISTRIBUTION; REPRODUCIBILITY OF RESULTS;

EID: 0034153465     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976600300015691     Document Type: Article

References (12)

1. Baldi, P., & Hornik, K. (1989). Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks, 2, 53-58.
2. Bourlard, H., & Kamp, Y. (1988). Auto-association by multilayer perceptrons and singular value decomposition. Biological Cybernetics, 59, 291-294.
3. Cottrell, G. W., & Munro, P. (1988). Principal component analysis of images via back propagation. In Proceedings of the Society of Photo-Optical Instrumentation Engineers. Cambridge, MA.
4. Hanson, S. J., & Kegl, J. (1987). PARSNIP: A connectionist network that learns natural language grammar from exposure to natural language sentences. In Proceedings of the Ninth Annual Conference on Cognitive Science.
5. Japkowicz, N. (1999). Concept-learning in the absence of counter-examples: An autoassociation-based approach to classification. Technical Report DCS-TR-390, Dept. of Computer Science, Rutgers Univ.
6. Japkowicz, N., Myers, C., & Gluck, M. A. (1995). A novelty detection approach to classification. In Proceedings of the Fourteenth Joint Conference on Artificial Intelligence (pp. 518-523).
7. Kruglyak, L. (1990). How to solve the N bit encoder problem with just two hidden units. Neural Computation, 2, 399-401.
8. Oja, E. (1983). Subspace methods of pattern recognition. New York: Wiley.
9. Petsche, T., Marcantonio, A., Darken, C., Hanson, S. J., Kuhn, G. M., & Santoso, I. (1996). A neural network autoassociator for induction motor failure prediction. In D. Toueretzky, M. Mozer, & M. Hasselmo (Eds.), Advances in neural information processing systems, 8. Cambridge, MA: MIT Press.
10. Phatak, D. S., Choi, H., & Koren, I. (1993). Construction of minimal N-2-N encoders for any N. Neural Computation, 5, 783-794.
11. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning internal representations by error propagation. In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel distributed processing (pp. 318-364). Cambridge, MA: MIT Press.
12. Zipser, D. (1989). Programming neural nets to do spatial computations. In N. Sharkey (Ed.), Models of cognition: A review of cognitive science. Norwood, NJ: Ablex.