Learning task-dependent distributed representations by backpropagation through structure

@inproceedings{Goller1996LearningTD,
  title={Learning task-dependent distributed representations by backpropagation through structure},
  author={Christoph Goller and Klaus Andreas},
  year={1996}
}
b b b b b b b b b b b b b b b b b b b Abstract While neural networks are very successfully applied to the processing of xed-length vectors and variable-length sequences, the current state of the art does not allow the eecient processing of structured objects of arbitrary shape (like logical terms, trees or graphs). We present a connectionist architecture together with a novel supervised learning scheme which is capable of solving inductive inference tasks on complex symbolic structures of… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Encoding of Labeled Graphs by Labeling RAAM

A Spe, Sperduti
Encoding of Labeled Graphs by Labeling RAAM • 1994

Structure sensitivity in connectionist models

L F Nic, Nicklasson
Proceedings of the 1993 Connectionist Models Summer School • 1994

Learning Recursive Distributed Representations for Holistic Computation

L Chr, Chrisman
Connection Science • 1991

Backpropagation Trough Time: What it Does and How to Do it

Paul J Wer, Werbos
Proceedings of the IEEE • 1990