Caesar AI Atlas

Backpropagation Through Structure

Caesar AI Atlas Definition

Backpropagation through structure is a gradient-based training technique for certain structured or recurrent neural network architectures. It extends the idea of propagating error through network components whose structure may reflect recursive or relational data.

Other Definitions

Backpropagation Through Structure Source

A gradient-based technique for training recurrent neural networks, proposed in a 1996 paper written by Christoph Goller and Andreas KΓΌchler.

Related Terms