Neural net architectures for temporal sequence processing

@inproceedings{Mozer1994NeuralNA,
  title={Neural net architectures for temporal sequence processing},
  author={Michael C. Mozer},
  year={1994}
}
I present a general taxonomy of neural net architectures for processing time-varying patterns. This taxonomy subsumes many existing architectures in the literature, and points to several promising architectures that have yet to be examined. Any architecture that processes timevarying patterns requires two conceptually distinct components: a short-term memory that holds on to relevant past events and an associator that uses the short-term memory to classify or predict. My taxonomy is based on a… CONTINUE READING
Highly Influential
This paper has highly influenced 18 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 177 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 47 references

Learning to represent state

  • J. Bachrach
  • Unpublished master's thesis, University of Mas-
  • 1988
Highly Influential
10 Excerpts

Attractor dynamics and parallelism in a connectionist sequential machine

  • M. I. Jordan
  • In
  • 1987
Highly Influential
5 Excerpts

Phoneme recognition

  • A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang
  • 1987
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…