Corpus ID: 209460946

TRADI: Tracking deep neural network weight distributions

@article{Franchi2019TRADITD,
  title={TRADI: Tracking deep neural network weight distributions},
  author={Gianni Franchi and Andrei Bursuc and Emanuel Aldea and S{\'e}verine Dubuisson and Isabelle Bloch},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.11316}
}
  • Gianni Franchi, Andrei Bursuc, +2 authors Isabelle Bloch
  • Published in ArXiv 2019
  • Computer Science, Mathematics
  • During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, accumulated over the descent towards the minimum is discarded. In this work we propose to make use of this knowledge and leverage it for computing the distributions of the weights of the DNN. This can… CONTINUE READING

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

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES

    Deep Learning Under Privileged Information Using Heteroscedastic Dropout

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Random Features for Large-Scale Kernel Machines

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural RGB®D Sensing: Depth and Uncertainty From a Video Camera

    VIEW 1 EXCERPT