Generalization of Elman Networks
Lists
Only you see this
Abstract
The Vapnik Chervonenkis dimension of Elman networks is infinite. Here, we find constructions leading to lower bounds for the fat shattering dimension that are linear resp. of order log2 in the input length even in the case of limited weights and inputs. Since finiteness of this magnitude is equivalent to learnability, there is no a priori guarantee for the generalization capability of Elman networks.
BibTeX
@inproceedings{hammer1997generalization,
author = {Barbara Hammer},
title = {{Generalization of Elman Networks}},
booktitle = {ICANN},
year = {1997},
url = {https://openreview.net/forum?id=e3BwBLE5gtH},
}Loading related content...