Backpropagation through structure
From HandWiki
Short description: Technique for training recursive neural nets
Backpropagation through structure (BPTS) is a gradient-based technique for training recursive neural nets (a superset of recurrent neural nets) and is extensively described in a 1996 paper written by Christoph Goller and Andreas Küchler.[1]
References
- ↑ Kuchler, Andreas (1996). "Learning Task-Dependent Distributed Representations by Backpropagation Through Structure". Proceedings of International Conference on Neural Networks (ICNN'96). 1. pp. 347–352. doi:10.1109/ICNN.1996.548916. ISBN 0-7803-3210-5.
 |  |
