Learning, invariance, and generalization in high-order neural networks

Applied Optics

Volumn 26, Issue 23, 1987, Pages 4972-4978

  Giles, Lee C ^a   Maxwell, Tom ^b  

^a AIR FORCE OFFICE OF SCIENTIFIC RESEARCH   (United States)

^b SFA INC   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATION; COMPUTER ANALYSIS; LEARNING; NERVE CELL NETWORK; STORAGE;

EID: 0023513717     PISSN: 1559128X     EISSN: 21553165     Source Type: Journal    
DOI: 10.1364/AO.26.004972     Document Type: Article

References (26)

1. T. Maxwell, C. L. Giles, and Y. C. Lee, “Generalization in Neural Networks: The Contiguity Problem,” inProceedings, IEEEInternational Conference on Neural Networks, San Diego(June 1987);
2. U. Maryland Physics Department Technical Report UMLPF 87-050 (June 1987).
3. T. Maxwell, C. L. Giles, Y. C. Lee, and H. H. Chen, “Transforme tion Invariance Using High Order Correlations in Neural Nc Architectures,” IEEE Trans. Syst. Man Cybern. SMC 86CH2364-8, 627 (1986).
4. T. Maxwell, C. L. Giles, Y. C. Lee, and H. H. Chen, “Nonlinea Dynamics of Artificial Neural Systems,” AIP Conf. Proc. 15. 299 (1986).
5. H. H. Chen, Y. C. Lee, T. Maxwell, G. Z. Sun, H. Y. Lee, and C. I Giles, “High Order Correlation Model for Associative Memory, AIP Conf. Proc. 151, 86 (1986).
6. Y. C. Lee, G. Doolen, H. H. Chen, G. Z. Sun, T. Maxwell, H.YLee, and C. L. Giles, “Machine Learning Using a Higher Orde Correlation Network,” Physica D 22, 276 (1986).
7. N. J. Nilsson, Learning Machines(McGraw-Hill, New York 1965).
8. F. Rosenblatt, Principles of Neurodynamics(Spartan, Nev York, 1962).
9. M. L. Minsky and S. Papert, Perceptrons(MIT Press, Cam bridge, MA, 1969).
10. D. Psaltis, J. Hong, and S. Venkatesh, “Shift Invariance ii Optical Associative Memories,” Proc. Soc. Photo-Opt. Instrum Eng. 625, 189 (1986);
11. D. Psaltis and C. H. Park, “Nonlineai Discriminant Functions and Associative Memories,” AIP Conf Proc. 151, 370 (1986).
12. R. A. Athale, H. H. Szu, C. B. Fried-lander, “Optical Implementation of Associative Memory wit! Controlled Nonlinearity in the Correlation Domain,” Optics Letters, vol. 11 #7, p 482 (1986).
13. Y. Owechko, G. J. Dunning, E Maron, and B. H. Soffer, “Holographic Associative Memorj with Nonlinearities in the Correlation Domain,” Applied Optics, vol. 26 #10, p 1900 (1987).
14. R. D. Griffin, C. L. Giles, J. N. Lee, T. Maxwell, and F. P. Pursel. “Optical Higher Order Neural Networks for Invariant Pattern Recognition,” presented at Optical Society of America Annual Meeting (Oct. 1987).
15. G. E. Hinton, “A Parallel Computation that Assigns Canonical Object-based Frames of Reference,” Proceedings of 7th International Joint Conference on Artificial Intelligence, ed. A. Drina, p 683 (1981).
16. J. A. Feldman, “Dynamic Connections in Neural Networks,” Biol. Cybern. 46, 27 (1982).
17. D. H. Ballard, “Cortical Connections and Parallel Processing: Structure and Function,” Behav. Brain Sci. 9, 67 (1986).
18. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning Internal Representations by Error Propagation,” Ch8inParallel Distributed Processing, vol 1., D. E. Rumelhart and J. L. McClelland, (MIT Press, Cambridge, MA, 1986).
19. T. J. Sejnowski, “Higher-Order Boltzmann Machines,” AIP Conf. Proc. 151, 398 (1986).
20. S. Grossberg, “Adaptive Pattern Classification and Universal Recoding, I: Parallel Development and Coding of Neural Feature Detectors,” Biol. Cybern. 23, 121 (1976);
21. D. E. Rumelhart and D. Zipser, “Feature Discovery by Competitive Learning,” Cognitive Sci. 9, 75 (1985).
22. D. Angluin and C. H. Smith, “Inductive Inference: Theory and Methods,” ACM Comput. Surv. 15, 237 (1983).
23. J. S. Denker and S. A. Solla, “Generalization and the Delta Rule,” presented at the Neural Networks for Computing Conference, Snowbird, UT (Apr. 1987).
24. J. H. Holland, K. J. Holyoak, R. E. Nisbett, and P. R. Thagard, Induction(MIT Press, Cambridge, MA, 1986).
25. P. Peretto and J. J. Niez, “Long Term Memory Storage Capacity of Multiconnected Neural Networks,” Biological Cybernetics54, p 53 (1986).
26. C. L. Giles, R. D. Griffin, T. P. Maxwell, “Encoding Invariances in Higher Order Neural Networks,” presented at IEEE conf. onNeural Information Processing Systems-Naturaland Synthetic, Denver, Co. Nov. 1987.