| Article ID: | iaor199541 |
| Country: | Netherlands |
| Volume: | 47 |
| Issue: | 3 |
| Start Page Number: | 207 |
| End Page Number: | 217 |
| Publication Date: | Dec 1993 |
| Journal: | Discrete Applied Mathematics |
| Authors: | Anthony Martin, Shawe-Taylor John |
| Keywords: | combinatorial analysis, neural networks |
A new proof of a result due to Vapnik is given. Its implications for the theory of PAC learnability are discussed, with particular reference to the learnability of functions taking values in a countable set. An application to the theory of artificial neural networks is then given.