Reducing the Dimensionality of Data with Neural Networks

@article{Hinton2006ReducingTD,
  title={Reducing the Dimensionality of Data with Neural Networks},
  author={Geoffrey E. Hinton and R. Salakhutdinov},
  journal={Science},
  year={2006},
  volume={313},
  pages={504 - 507}
}
High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such “autoencoder” networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than… Expand
12,397 Citations
Dimensionality Reduction Using Neural Networks
  • 4
  • Highly Influenced
  • PDF
Training neural networks on high-dimensional data using random projection
  • 20
  • PDF
Index-learning of unsupervised low dimensional embeddings
  • PDF
Dimensionality Reduction Applied to Time Response of Linear Systems Using Autoencoders
Deep Bottleneck Classifiers in Supervised Dimension Reduction
  • 6
  • Highly Influenced
  • PDF
From Principal Subspaces to Principal Components with Linear Autoencoders
  • E. Plaut
  • Mathematics, Computer Science
  • ArXiv
  • 2018
  • 34
  • PDF
Random Projection in Deep Neural Networks
  • 1
  • PDF
1 DIMENSIONALITY REDUCTION USING NEURAL NETWORKS
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Dimension Reduction by Local Principal Component Analysis
  • 618
  • PDF
Nonlinear dimensionality reduction by locally linear embedding.
  • 13,123
  • PDF
A Fast Learning Algorithm for Deep Belief Nets
  • 11,894
  • PDF
Replicator neural networks for universal optimal source coding.
  • 128
Learning sets of filters using back-propagation
  • 123
  • PDF
In Advances in Neural Information Processing Systems
  • 3,563
Neural networks and physical systems with emergent collective computational abilities.
  • J. Hopfield
  • Computer Science, Medicine
  • Proceedings of the National Academy of Sciences of the United States of America
  • 1982
  • 12,789
  • PDF
Neural Computation
  • 1,496
  • PDF
Machine learning
  • 13,754
  • PDF
...
1
2
3
4
5
...