Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks

@article{Hinz2018SpeedingUT,
  title={Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks},
  author={Tobias Hinz and Nicol{\'a}s Navarro and Sven Magg and Stefan Wermter},
  journal={International Journal of Computational Intelligence and Applications},
  year={2018},
  volume={17},
  pages={1850008:1-1850008:15}
}
  • Tobias Hinz, Nicolás Navarro, +1 author Stefan Wermter
  • Published in
    International Journal of…
    2018
  • Computer Science
  • Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a give... 

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 21 CITATIONS

    Optimization of Hyper-parameter for CNN Model using Genetic Algorithm

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Regularize, Expand and Compress: NonExpansive Continual Learning

    • Jie Zhang, Junting Zhang, +4 authors Yalin Wang
    • Computer Science
    • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
    • 2020
    VIEW 1 EXCERPT
    CITES METHODS

    Weighted Random Search for CNN Hyperparameter Optimization

    VIEW 1 EXCERPT
    CITES METHODS

    Bayesian Hyperparameter Optimization with BoTorch, GPyTorch and Ax

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    Enhancing Clinical Name Entity Recognition Based on Hybrid Deep Learning Scheme

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 33 REFERENCES

    Random Search for Hyper-Parameter Optimization

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Practical Block-Wise Neural Network Architecture Generation

    VIEW 2 EXCERPTS

    Bayesian optimization for conditional hyperparameter spaces

    Neural Architecture Search with Reinforcement Learning

    VIEW 2 EXCERPTS