A Dynamical Approach to Temporal Pattern Processing

W. Scott Stornetta, Tad Hogg, Bernardo A. Huberman

NeurIPS 1987 pp. 750-759

/neurips/1987/stornetta1987neurips-dynamical/

Abstract

Recognizing patterns with temporal context is important for such tasks as speech recognition, motion detection and signature verification. We propose an architecture in which time serves as its own representation, and temporal context is encoded in the state of the nodes. We contrast this with the approach of replicating portions of the architecture to represent time.

PDF NeurIPS Semantic Scholar

Cite

Text

Stornetta et al. "A Dynamical Approach to Temporal Pattern Processing." Neural Information Processing Systems, 1987.

Markdown

[Stornetta et al. "A Dynamical Approach to Temporal Pattern Processing." Neural Information Processing Systems, 1987.](https://mlanthology.org/neurips/1987/stornetta1987neurips-dynamical/)

BibTeX

@inproceedings{stornetta1987neurips-dynamical,
  title     = {{A Dynamical Approach to Temporal Pattern Processing}},
  author    = {Stornetta, W. Scott and Hogg, Tad and Huberman, Bernardo A.},
  booktitle = {Neural Information Processing Systems},
  year      = {1987},
  pages     = {750-759},
  url       = {https://mlanthology.org/neurips/1987/stornetta1987neurips-dynamical/}
}