Jump to content

Backpropagation through structure

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Biscuittin (talk | contribs) at 22:29, 5 May 2015 (add cat). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

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

  1. ^ Kuchler, Andreas. "Learning Task-Dependent Distributed Representations by Backpropagation Through Structure". psu.edu. CiteSeerx: 10.1.1.49.1968.
Retrieved from "https://en.wikipedia.org/w/index.php?title=Backpropagation_through_structure&oldid=661016288"