Learning task-dependent distributed representations by backpropagation through structure

@article{Goller1996LearningTD,
title={Learning task-dependent distributed representations by backpropagation through structure},
author={C. Goller and A. K{\"u}chler},
journal={Proceedings of International Conference on Neural Networks (ICNN'96)},
year={1996},
volume={1},
pages={347-352 vol.1}
}

Proceedings of International Conference on Neural Networks (ICNN'96)

While neural networks are very successfully applied to the processing of fixed-length vectors and variable-length sequences, the current state of the art does not allow the efficient processing of structured objects of arbitrary shape (like logical terms, trees or graphs. [...] Key Method The major difference of our approach compared to others is that the structure-representations are exclusively tuned for the intended inference task.Expand