Backpropagation through structure
Technique for training recursive neural networks From Wikipedia, the free encyclopedia
Backpropagation through structure (BPTS) is a gradient-based technique for training recursive neural networks, proposed in a 1996 paper written by Christoph Goller and Andreas Küchler.[1]
This article needs additional citations for verification. (May 2015) |
References
Wikiwand - on
Seamless Wikipedia browsing. On steroids.