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]

References

Loading related searches...

Wikiwand - on

Seamless Wikipedia browsing. On steroids.