Corpus ID: 6949717

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks

@article{Zeiler2013StochasticPF,
  title={Stochastic Pooling for Regularization of Deep Convolutional Neural Networks},
  author={Matthew D. Zeiler and R. Fergus},
  journal={CoRR},
  year={2013},
  volume={abs/1301.3557}
}
  • Matthew D. Zeiler, R. Fergus
  • Published 2013
  • Computer Science, Mathematics
  • CoRR
  • We introduce a simple and effective method for regularizing large convolutional neural networks. [...] Key Method The approach is hyper-parameter free and can be combined with other regularization approaches, such as dropout and data augmentation. We achieve state-of-the-art performance on four image datasets, relative to other approaches that do not utilize data augmentation.Expand Abstract
    687 Citations
    Max-Pooling Dropout for Regularization of Convolutional Neural Networks
    • Haibing Wu, Xiaodong Gu
    • Computer Science, Mathematics
    • ICONIP
    • 2015
    • 53
    • Highly Influenced
    • PDF
    General Stochastic Networks for Classification
    • 21
    • PDF
    An Improved Pooling Scheme for Convolutional Neural Networks
    • 1
    Restricted stochastic pooling for convolutional neural network
    • 1
    • Highly Influenced
    REGP: A NEW POOLING ALGORITHM FOR DEEP CONVOLUTIONAL NEURAL NETWORKS
    • 2
    • PDF
    A Novel Pooling Method for Regularization of Deep Neural networks
    A New Pooling Method For Improvement OfGeneralization Ability In Deep Convolutional Neural Networks
    • 1
    • Highly Influenced
    • PDF
    Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
    • 311
    • PDF
    Mixed Pooling for Convolutional Neural Networks
    • 110
    • PDF
    Towards dropout training for convolutional neural networks
    • Haibing Wu, Xiaodong Gu
    • Computer Science, Medicine
    • Neural Networks
    • 2015
    • 133
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 19 REFERENCES
    Adaptive deconvolutional networks for mid and high level feature learning
    • 819
    • PDF
    Neural Networks: Tricks of the Trade
    • 670
    • PDF
    Beyond spatial pyramids: Receptive field learning for pooled image features
    • 281
    • PDF
    Learning Multiple Layers of Features from Tiny Images
    • 9,348
    • PDF
    Convolutional neural networks applied to house numbers digit classification
    • 384
    • Highly Influential
    • PDF
    Improving neural networks by preventing co-adaptation of feature detectors
    • 4,955
    • Highly Influential
    • PDF
    Best practices for convolutional neural networks applied to visual document analysis
    • 1,944
    • PDF
    Rectified Linear Units Improve Restricted Boltzmann Machines
    • 9,232
    • PDF
    Reading Digits in Natural Images with Unsupervised Feature Learning
    • 2,440
    • PDF