Sparse representations in deep learning for noise-robust digit classification

@article{Ghifary2013SparseRI,
  title={Sparse representations in deep learning for noise-robust digit classification},
  author={Muhammad Ghifary and W. Kleijn and M. Zhang},
  journal={2013 28th International Conference on Image and Vision Computing New Zealand (IVCNZ 2013)},
  year={2013},
  pages={340-345}
}
Many sparse regularization methods for encouraging succinct hierarchical features of deep architectures have been proposed, but there is still a lack of studies that compare them. We present a comparison of several sparse regularization methods in deep learning with respect to the performance of a noisy digit classification task under varying size of training samples. We also propose a deep hybrid architecture built from a particular combination of sparse auto-encoders and Restricted Boltzmann… Expand
4 Citations

References

SHOWING 1-10 OF 32 REFERENCES
Sparse Feature Learning for Deep Belief Networks
  • 747
  • Highly Influential
  • PDF
Are sparse representations really relevant for image classification?
  • 205
  • PDF
Classification using discriminative restricted Boltzmann machines
  • 738
  • PDF
Efficient Learning of Sparse Representations with an Energy-Based Model
  • 1,072
  • PDF
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
  • 2,312
  • PDF
Greedy Layer-Wise Training of Deep Networks
  • 2,648
  • Highly Influential
  • PDF
A Fast Learning Algorithm for Deep Belief Nets
  • 11,678
  • PDF
Sparse Representation for Color Image Restoration
  • 1,617
  • PDF
Reducing the Dimensionality of Data with Neural Networks
  • 12,123
  • PDF
...
1
2
3
4
...