Bounding Sample Size with the Vapnik-Chervonenkis Dimension
A proof that a concept class is learnable provided the Vapnik-Chervonenkis dimension is finite is given. The proof is more explicit than previous proofs and introduces two new parameters which allow bounds on the sample size obtained to be improved by a factor of approximately 4 log2(e).
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
1993.
|
| Subjects: | |
| Online Access: | Get fulltext |