# Learning Wake-Sleep Recurrent Attention Models Source: [Learning Wake-Sleep Recurrent Attention Models]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:12:29.814Z Authors: Jimmy Ba, Roger Grosse, Ruslan Salakhutdinov, Brendan Frey Published: 2015-09-22T23:52:30.000Z ## Abstract 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 method for training stochastic attention networks which improves posterior inference and which reduces the variability in the stochastic gradients. We show that our method can greatly speed up the training time for stochastic attention networks in the domains of image classification and caption generation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()