Corpus ID: 15607207

Generalising the Discriminative Restricted Boltzmann Machine

@article{Cherla2016GeneralisingTD,
  title={Generalising the Discriminative Restricted Boltzmann Machine},
  author={Srikanth Cherla and Son N. Tran and Tillman Weyde and Artur S. d'Avila Garcez},
  journal={ArXiv},
  year={2016},
  volume={abs/1604.01806}
}
  • Srikanth Cherla, Son N. Tran, +1 author Artur S. d'Avila Garcez
  • Published in ArXiv 2016
  • Computer Science, Mathematics
  • We present a novel theoretical result that generalises the Discriminative Restricted Boltzmann Machine (DRBM). While originally the DRBM was defined assuming the {0, 1}-Bernoulli distribution in each of its hidden units, this result makes it possible to derive cost functions for variants of the DRBM that utilise other distributions, including some that are often encountered in the literature. This is illustrated with the Binomial and {-1, +1}-Bernoulli distributions here. We evaluate these two… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    2
    Twitter Mentions

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES

    Classification using discriminative restricted Boltzmann machines

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    NewsWeeder: Learning to Filter Netnews

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Acoustic Modeling Using Deep Belief Networks

    VIEW 1 EXCERPT