Helmholtz Machines and Wake-Sleep Learning

By Peter S. Dayan. 2000

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

Citations in the corpus

Variational Inference with Normalizing Flows (2015, methodology): “A second important practice is that the approximate posterior distribution q φ ( · ) is represented using a recognition model or inference network (Rezende et al., 2014; Dayan, 2000; Gershman & Goodman, 2014; Kingma & Welling, 2014).”
Hierarchical Variational Models (2015, background): “Inference networks (Dayan, 2000; Stuhlmüller et al., 2013; Kingma and Welling, 2014; Rezende et al., 2014) amortize the cost of estimating these local variational parameters by tying them together through a neural network.”
Stochastic Back-propagation and Variational Inference in Deep Latent Gaussian Models (2014, methodology): “80 Wake-Sleep (Dayan, 2000) 91”
Deep neural networks: a new framework for modelling biological vision and brain information processing (2015, methodology): “The learning can be performed using the wake-sleep algorithm (Hinton et al. 1995; Dayan 2000).”
Stochastic variational learning in recurrent spiking networks (2014, methodology): “These interesting properties of the variational approximation have been explored by a diversity of models (Dayan, 2000; Friston and Stephan, 2007; Jimenez Rezende et al., 2011; Brea et al., 2013; Nessler et al., 2013).”
Stochastic Backpropagation and Approximate Inference in Deep Generative Models (2014, methodology): “A number of approaches are known and widely used, and include: mean-field variational EM (Beal, 2003); the wake-sleep algorithm (Dayan, 2000); and stochastic variational methods and related control-variate estimators (Wilson, 1984; Williams, 1992; Hoffman et al.”
Merging chrominance and luminance in early, medium, and late fusion using Convolutional Neural Networks (2015, methodology): “More information about the HM and the wake-sleep algorithm can be found in [Dayan and Hinton, 1996; Dayan, 2000; Kirby, 2006].”