Improving neural networks by preventing co-adaptation of feature detectors

By Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov. 2012

8,038 citations recorded by the source corpus.

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random "dropout" gives big improvements on many benchmark tasks and sets new records for speech and object recognition.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Mohit Bansal
  3. Quoc V. Le
  4. Jianfeng Gao
  5. Sergey Levine
  6. Percy Liang
  7. Kyunghyun Cho
  8. Ruslan Salakhutdinov

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Dacheng Tao
  3. Xiaogang Wang
  4. Trevor Darrell
  5. Ming-Hsuan Yang
  6. Jitendra Malik
  7. Andrew Zisserman
  8. Yi Yang

In Model Architectures

  1. Yoshua Bengio
  2. Quoc V. Le
  3. Kyunghyun Cho
  4. Kaiming He
  5. Ruslan Salakhutdinov
  6. Alan L. Yuille
  7. Aaron C. Courville
  8. Dacheng Tao

In Optimization & Training

  1. Yoshua Bengio
  2. Quoc V. Le
  3. Frank Hutter
  4. Aaron C. Courville
  5. Kyunghyun Cho
  6. Roger Baker Grosse
  7. Stefano Soatto
  8. Ruslan Salakhutdinov

Citations in the corpus