Reverse TDNN: An Architecture for Trajectory Generation

Abstract

The backpropagation algorithm can be used for both recognition and gen(cid:173) eration of time trajectories. When used as a recognizer, it has been shown that the performance of a network can be greatly improved by adding structure to the architecture. The same is true in trajectory generation. In particular a new architecture corresponding to a "reversed" TDNN is proposed. Results show dramatic improvement of performance in the gen(cid:173) eration of hand-written characters. A combination of TDNN and reversed TDNN for compact encoding is also suggested.

Cite

Text

Simard and Le Cun. "Reverse TDNN: An Architecture for Trajectory Generation." Neural Information Processing Systems, 1991.

Markdown

[Simard and Le Cun. "Reverse TDNN: An Architecture for Trajectory Generation." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/simard1991neurips-reverse/)

BibTeX

@inproceedings{simard1991neurips-reverse,
  title     = {{Reverse TDNN: An Architecture for Trajectory Generation}},
  author    = {Simard, Patrice and Le Cun, Yann},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {579-588},
  url       = {https://mlanthology.org/neurips/1991/simard1991neurips-reverse/}
}