Corpus ID: 86522127

Uncertainty in Deep Learning

@inproceedings{Gal2016UncertaintyID,
  title={Uncertainty in Deep Learning},
  author={Yarin Gal},
  year={2016}
}
  • Yarin Gal
  • Published 2016
  • Computer Science
  • Deep learning has attracted tremendous attention from researchers in various fields of information engineering such as AI, computer vision, and language processing [Kalchbrenner and Blunsom, 2013; Krizhevsky et al., 2012; Mnih et al., 2013], but also from more traditional sciences such as physics, biology, and manufacturing [Anjos et al., 2015; Baldi et al., 2014; Bergmann et al., 2014]. Neural networks, image processing tools such as convolutional neural networks, sequence processing models… CONTINUE READING
    659 Citations
    Benchmarks for Bayesian Deep Learning: Image Segmentation
    • Highly Influenced
    • PDF
    DEAL: Deep Evidential Active Learning for Image Classification
    • Highly Influenced
    • PDF
    Uncertainty estimation in deep learning with application to spoken language assessment
    • 10
    • Highly Influenced
    • PDF
    DEEP ENSEMBLE BAYESIAN ACTIVE LEARNING: AD-
    • Highly Influenced
    DEEP ENSEMBLE BAYESIAN ACTIVE LEARNING : ADRESSING
    • Highly Influenced
    Novelty Detection in Convolutional Neural Networks Using Density Forests
    • 1
    • PDF
    Deep Bayesian Active Learning with Image Data
    • 498
    • PDF
    Uncertainty Quantification in Deep Residual Neural Networks
    • 1
    • Highly Influenced
    • PDF
    Example weighting for deep representation learning
    • PDF

    References

    SHOWING 1-10 OF 142 REFERENCES
    Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
    • 376
    • PDF
    Dropout as a Bayesian Approximation : Insights and Applications
    • Yg, UK CAM.AC.
    • 2015
    • 73
    • PDF
    Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
    • 2,718
    • PDF
    Deep Networks with Stochastic Depth
    • 927
    • PDF
    Learning Multiple Layers of Features from Tiny Images
    • 10,432
    • PDF
    Adaptive dropout for training deep neural networks
    • 230
    • PDF
    Scaling learning algorithms towards AI
    • 994
    • PDF
    On Fast Dropout and its Applicability to Recurrent Networks
    • 51
    • PDF
    ImageNet classification with deep convolutional neural networks
    • 59,458
    • Highly Influential
    • PDF
    RNNDROP: A novel dropout for RNNS in ASR
    • 75
    • PDF