Corpus ID: 7514628

Forward-backward retraining of recurrent neural networks

@inproceedings{Senior1995ForwardbackwardRO,
  title={Forward-backward retraining of recurrent neural networks},
  author={Andrew W. Senior and Anthony J. Robinson},
  booktitle={NIPS},
  year={1995}
}
  • Andrew W. Senior, Anthony J. Robinson
  • Published in NIPS 1995
  • Computer Science
  • This paper describes the training of a recurrent neural network as the letter posterior probability estimator for a hidden Markov model, off-line handwriting recognition system. The network estimates posterior distributions for each of a series of frames representing sections of a handwritten word. The supervised training algorithm, backpropagation through time, requires target outputs to be provided for each frame. Three methods for deriving these targets are presented. A novel method based… CONTINUE READING

    Figures and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 32 CITATIONS

    Framewise and CTC training of Neural Networks for handwriting recognition

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    Understanding speech recognition using correlation-generated neural network targets

    • Yonghong Yan
    • Computer Science
    • IEEE Trans. Speech Audio Process.
    • 1999
    VIEW 2 EXCERPTS
    CITES RESULTS & METHODS

    Stabilize Sequence Learning with Recurrent Neural Networks by Forced Alignment

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Hidden Neural Networks

    VIEW 1 EXCERPT
    CITES METHODS

    Cascading BLSTM networks for handwritten word recognition

    VIEW 1 EXCERPT
    CITES METHODS

    A Lexicon Verification Strategy in a BLSTM Cascade Framework

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    1997
    2020

    CITATION STATISTICS

    • 2 Highly Influenced Citations

    References

    Publications referenced by this paper.
    SHOWING 1-5 OF 5 REFERENCES

    An introduction to hidden Markov models

    VIEW 2 EXCERPTS

    The application ofrecuIIent nets to phone probability estimation

    • Bradford Books. SANTINI, S. and DEL BIMBO, A
    • 1994