On the difficulty of training Recurrent Neural Networks
By: Researcher
Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
| Authors | Tomas Mikolov, Razvan Pascanu, Yoshua Bengio |
| Journal/Conference Name | 30th International Conference on Machine Learning, ICML 2013 |
| Paper Category | Artificial Intelligence |
| Paper Abstract | There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying issues by exploring these problems from an analytical, a geometric and a dynamical systems perspective. Our analysis is used to justify a simple yet effective solution. We propose a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section. |
| Date of publication | 2012 |
| Code Programming Language | Multiple |
| Comment |
Copyright Researcher 2022