Lower bound on VC-dimension by local shattering

Neural Computation

Volumn 9, Issue 4, 1997, Pages 771-776

  Erlich, Yossi ^a,d   Chazan, Dan ^b   Petrack, Scott ^c   Levy, Avraham ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b IBM HAIFA RESEARCH LAB   (Israel)

^c Vocaltec Ltd   (Israel)

^d IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0040314238     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1997.9.4.771     Document Type: Article

References (6)

1. Erlich, Y. (1996). On HMM based speech recognition using the MCE approach. M.Sc. thesis, Technion-Israel Institute of Technology. (Note: written in Hebrew; abstract in English.)
2. Erlich, Y., Merhav, N., & Chazan, D. (1996). On the MCE approach for training HMM based speech recognition systems. Unpublished manuscript.
3. Korian, P., & Sontag, E. (1996). Neural networks with quadratic VC dimension. In D. S. Touretzky, M. C. Moser, & M. E. Hasselmo (Eds.), Advances in Neural Information Processing Systems (vol. 8, pp. 197-203). Cambridge, MA: MIT Press.
4. Lee, W. S., Bartlett, P. L., & Williamson, R. C. (1995). Lower bounds on the VC dimension of smoothly parameterized function classes. Neural Computation, 7, 1040-1053.
5. Lee, W. S., Bartlett, P. L., & Williamson, R. C. (1997). Correction to "Lower Bounds on the VC Dimension of Smoothly Parameterized Function Classes." Neural Computation, 9, 765-769.
6. Sontag, E. (1992). Feedforward nets for interpolation and classification. J. Comp. Syst. Sci., 45, 20-48.