“Backpropagation through structure”的意思、由来-开放百科全书

词条

Backpropagation through structure

释义

References

{{refimprove|date=May 2015}}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. ^{{cite paper|last1=Kuchler|first1=Andreas|title=Learning Task-Dependent Distributed Representations by Backpropagation Through Structure|citeseerx = 10.1.1.49.1968|website=psu.edu|url=https://pdfs.semanticscholar.org/794e/6ed81d21f1bf32a0fd3be05c44c1fa362688.pdf}}

1 : Artificial neural networks

随便看

开放百科全书收录14589846条英语、德语、日语等多语种百科知识，基本涵盖了大多数领域的百科知识，是一部内容自由、开放的电子版国际百科全书。