Geometry of admissible parameter region in neural learning

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

Volumn E79-A, Issue 6, 1996, Pages 938942-

  Ikedat, Kazushi ^a,c   Amari, Shun Ichi ^b  

^a KANAZAWA UNIVERSITY   (Japan)

^b UNIVERSITY OF TOKYO   (Japan)

^c RIKEN   (Japan)

Author keywords

Convex hull; Learning curve; Perceptron; Stochastic geometry

Indexed keywords

EID: 33746218431     PISSN: 09168508     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (11)

1. [I] S. Amari, "A universal theorem on learning curves," Neural Networks, vol.6, pp. 161166, 1993
2. S. Amari, N. Fujita, and S. Shinomoto, "Four types of learning curves," Neural Computation, vol.4, pp.604617, 1992
3. S. Amari and N. Murata, "Statistical theory of learning curves under entropie loss criterion," Neural Computation, vol.5, pp.140153, 1993
4. E.B. Baum and D. Haussler, "What size net gives valid generalization?," Neural Computation, vol.1, pp.151160, 1989
5. T.M. Cover, "Geometrical and statistical properties of lin ear threshold devices," SEL, 64052, Stanford Univ., 1964
6. B. Efron, "The convex hull of a random set of points," Biometrika, vol.52, pp.331343, 1965
7. D. Haussier, M. Kearns, and R. Schapire, "Bounds on the sample complexity of Bayesian learning," UCSCCRL, 91 44, UCSC, 1992
8. E. Levin, N. Tishby, and S.A. Solla, "A statistical approach to learning and generalization in layered neural networks," Proc. IEEE, vol.78, pp.15681574, 1990
9. M. Opper and D. Haussler, "Calculation of the learning curve of bayes optimal classification on algorithm for learning a perceptron with noise," Proc. Ann. Workshop Comp. Learning Theory, vol.4, pp.7587, 1991.
10. H.S. Seung, H. Sompolinsky, and N. Tishby, "Statistical mechanics of learning from examples," Physical Review A, vol.45, pp.60566091, 1992
11. L.G. Valiant, "A theory of the learnable," Comm. ACM, vol.27, pp.11341142, 1984.