Title :
Improving the generalisation of the N-tuple classifier using the effective VC dimension
Author :
Bradshaw, N.P. ; Aleksander, I.
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
fDate :
9/26/1996 12:00:00 AM
Abstract :
The VC dimension of an n-tuple classifier predicts poorer generalisation performance than is found in practice. The effective VC dimension of the classifier for a Gaussian input distribution is calculated empirically and shown to be significantly lower than the true VC dimension. Thus better generalisation can be predicted without the risk of over-fitting
Keywords :
Gaussian distribution; learning (artificial intelligence); pattern classification; Gaussian input distribution; N-tuple classifier; effective VC dimension; generalisation performance;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19961264
