Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

@inproceedings{Lee2009ConvolutionalDB,
  title={Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations},
  author={H. Lee and Roger B. Grosse and R. Ranganath and A. Ng},
  booktitle={ICML '09},
  year={2009}
}
There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks. Scaling such models to full-sized, high-dimensional images remains a difficult problem. To address this problem, we present the convolutional deep belief network, a hierarchical generative model which scales to realistic image sizes. This model is translation-invariant and supports efficient bottom-up and top-down probabilistic inference. Key to our approach is probabilistic max… Expand
2,335 Citations
Learning deep generative models
  • 281
  • PDF
Learning with Hierarchical-Deep Models
  • 197
  • PDF
Learning Deep Representations, Embeddings and Codes from the Pixel Level of Natural and Medical Images
  • Highly Influenced
  • PDF
Hierarchical Convolutional Deep Learning in Computer Vision
  • 36
  • Highly Influenced
  • PDF
A probabilistic model for recursive factorized image features
  • 8
  • PDF
A Deep Generative Deconvolutional Image Model
  • 37
  • PDF
Detection guided deconvolutional network for hierarchical feature learning
  • 10
  • Highly Influenced
Learning to Learn with Compound HD Models
  • 31
  • PDF
Temporal Continuity Learning for Convolutional Deep Belief Networks
  • 4
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-9 OF 9 REFERENCES
A Fast Learning Algorithm for Deep Belief Nets
  • 11,889
  • Highly Influential
  • PDF
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
  • 1,031
  • Highly Influential
  • PDF
Efficient Learning of Sparse Representations with an Energy-Based Model
  • 1,089
  • Highly Influential
  • PDF
Multiclass Object Recognition with Sparse, Localized Features
  • Jim Mutch, D. Lowe
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 548
  • Highly Influential
  • PDF
The “independent components” of natural scenes are edge filters
  • 2,317
  • Highly Influential
  • PDF
Deep learning via semi-supervised embedding
  • 478
  • Highly Influential
  • PDF
Reducing the Dimensionality of Data with Neural Networks
  • 12,395
  • Highly Influential
  • PDF
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
  • S. Lazebnik, C. Schmid, J. Ponce
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 8,143
  • Highly Influential
  • PDF
Sparse deep belief network model for visual area V 2 . Advances in Neural Information Processing Systems
  • 2008