Corpus ID: 15127402

Visualizing Higher-Layer Features of a Deep Network

@inproceedings{Erhan2009VisualizingHF,
  title={Visualizing Higher-Layer Features of a Deep Network},
  author={D. Erhan and Yoshua Bengio and Aaron C. Courville and P. Vincent},
  year={2009}
}
  • D. Erhan, Yoshua Bengio, +1 author P. Vincent
  • Published 2009
  • Computer Science
  • Deep architectures have demonstrated state-of-the-art results in a variety of settings, especially with vision datasets. Beyond the model definitions and the quantitative analyses, there is a need for qualitative comparisons of the solutions learned by various deep architectures. The goal of this paper is to find good qualitative interpretations of high level features represented by such models. To this end, we contrast and compare several techniques applied on Stacked Denoising Autoencoders… CONTINUE READING
    726 Citations
    Visualizing stacked autoencoder language learning
    • 1
    • PDF
    Visualizing and Understanding Convolutional Networks
    • 8,967
    • PDF
    Generative adversarial network for visualizing convolutional network
    • 1
    Towards Better Analysis of Deep Convolutional Neural Networks
    • 255
    • PDF
    Interpretability of deep learning models: A survey of results
    • S. Chakraborty, Richard Tomsett, +12 authors Prudhvi Gurram
    • Computer Science
    • 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI)
    • 2017
    • 114
    • PDF
    Exploring LOTS in Deep Neural Networks
    • Highly Influenced
    • PDF
    TopoAct: Exploring the Shape of Activations in Deep Learning
    • 5
    • PDF
    Deep Insights into Convolutional Networks for Video Recognition
    • 7
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 20 REFERENCES
    Learning Deep Architectures for AI
    • 6,426
    • PDF
    Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
    • 2,283
    • Highly Influential
    • PDF
    Greedy Layer-Wise Training of Deep Networks
    • 2,594
    • PDF
    An empirical evaluation of deep architectures on problems with many factors of variation
    • 845
    • PDF
    Extracting and composing robust features with denoising autoencoders
    • 4,289
    • PDF
    Sparse deep belief net model for visual area V2
    • 975
    • Highly Influential
    • PDF
    Exploring Strategies for Training Deep Neural Networks
    • 910
    • PDF
    Sparse Feature Learning for Deep Belief Networks
    • 745
    • PDF
    Deep learning via semi-supervised embedding
    • 444
    • PDF
    Modeling image patches with a directed hierarchy of Markov random fields
    • 135
    • PDF