Deep Residual Autoencoders for Expectation Maximization-Inspired Dictionary Learning.

@article{Tolooshams2020DeepRA,
  title={Deep Residual Autoencoders for Expectation Maximization-Inspired Dictionary Learning.},
  author={Bahareh Tolooshams and S. Dey and Demba E. Ba},
  journal={IEEE transactions on neural networks and learning systems},
  year={2020},
  volume={PP}
}
We introduce a neural-network architecture, termed the constrained recurrent sparse autoencoder (CRsAE), that solves convolutional dictionary learning problems, thus establishing a link between dictionary learning and neural networks. Specifically, we leverage the interpretation of the alternating-minimization algorithm for dictionary learning as an approximate expectation-maximization algorithm to develop autoencoders that enable the simultaneous training of the dictionary and regularization… Expand
8 Citations
Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
  • 5
  • PDF
Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution
  • PDF
Randnet: Deep Learning with Compressed Measurements of Images
  • 5
  • PDF
Deeply-Sparse Signal rePresentations (D$\text{S}^2$P)
  • Demba E. Ba
  • Computer Science, Engineering
  • IEEE Transactions on Signal Processing
  • 2020
  • PDF
Adversarial Robustness of Supervised Sparse Coding
  • 2
  • PDF

References

SHOWING 1-10 OF 45 REFERENCES
SCALABLE CONVOLUTIONAL DICTIONARY LEARNING WITH CONSTRAINED RECURRENT SPARSE AUTO-ENCODERS
  • 15
  • PDF
Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization
  • 144
  • Highly Influential
  • PDF
k-Sparse Autoencoders
  • 241
  • Highly Influential
  • PDF
Learned Convolutional Sparse Coding
  • Hillel Sreter, R. Giryes
  • Computer Science, Engineering
  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
  • 48
  • Highly Influential
  • PDF
Variational Lossy Autoencoder
  • 403
  • PDF
On the Convergence of Adam and Beyond
  • 1,054
  • PDF
Adam: A Method for Stochastic Optimization
  • 61,209
  • PDF
Convolutional Neural Networks Analyzed via Convolutional Sparse Coding
  • 172
  • PDF
Rethinking the CSC Model for Natural Images
  • 21
  • PDF
Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures
  • 224
  • PDF
...
1
2
3
4
5
...