Learning Wake-Sleep Recurrent Attention Models

@inproceedings{Ba2015LearningWR,
  title={Learning Wake-Sleep Recurrent Attention Models},
  author={Jimmy Ba and Roger B. Grosse and Ruslan Salakhutdinov and Brendan J. Frey},
  booktitle={NIPS},
  year={2015}
}
Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they remain difficult to train because of intractable posterior inference and high variance in the stochastic gradient estimates. Borrowing techniques from the literature on training deep generative models, we present the Wake-Sleep Recurrent Attention Model, a… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 34 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.

Similar Papers

Loading similar papers…