Second Order Derivatives for Network Pruning: Optimal Brain Surgeon (1993)
by
Babak Hassibi
,
David G. Stork
,
Stork Crc. Ricoh. Com
| Venue: | Advances in Neural Information Processing Systems 5 |
| Citations: | 148 - 2 self |
BibTeX
@INPROCEEDINGS{Hassibi93secondorder,
author = {Babak Hassibi and David G. Stork and Stork Crc. Ricoh. Com},
title = {Second Order Derivatives for Network Pruning: Optimal Brain Surgeon},
booktitle = {Advances in Neural Information Processing Systems 5},
year = {1993},
pages = {164--171},
publisher = {Morgan Kaufmann}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We investigate the use of information from all second order derivatives of the error function to perform network pruning (i.e., removing unimportant weights from a trained network) in order to improve generalization and increase the speed of further training.
Citations
| 2304 | Learning Internal Representations by Error Propagation - Rumelhart, Hinton, et al. - 1986 |
| 89 | Introduction to the theory of neural computation (Addison-Wesley - Hertz, Krogh, et al. - 1991 |
| 4 | A Frobenius approximation reduction method (FARM) for determining optimal number of hidden units - Kung, Hu - 1991 |
