Wake-sleep algorithm ==================== The wake-sleep algorithm is an unsupervised learning algorithm for deep generative models, especially Helmholtz Machines. The algorithm is similar to the expectation-maximization algorithm, and optimizes the model likelihood for observed data. The name of the algorithm derives from its use of two learning phases, the “wake” phase and the “sleep” phase, which are performed alternately. It can be conceived as a model for learning in the brain, but is also being applied for machine learning. The wake-sleep algorithm is an unsupervised learning algorithm for deep generative models, especially Helmholtz Machines. The algorithm is similar to the expectation-maximization algorithm, and optimizes the model likelihood for observed data. The name of the algorithm derives from its use of two learning phases, the “wake” phase and the “sleep” phase, which are performed alternately. It can be conceived as a model for learning in the brain, but is also being applied for machine learning. ==See also== Restricted Boltzmann machine, a type of neural net that is trained with a conceptually similar algorithm. Helmholtz machine, a neural network model trained by the wake-sleep algorithm. ==References== REFERENCES ---------- BIBLIOGRAPHY (BibTeX) -------------------- @article{ref0, title = {Wake-sleep algorithm}, url = {https://encyclopegia.org/a/wake-sleep-algorithm} } BIBLIOGRAPHY (RIS) ------------------- TY - JOUR TI - Wake-sleep algorithm UR - https://encyclopegia.org/a/wake-sleep-algorithm ER - CITE THIS ARTICLE ---------------- Cite this article: Wake-sleep algorithm Derived from: https://en.wikipedia.org/w/index.php?oldid=1192002807 Licence: CC BY-SA 4.0 Snapshot: enwiki-001192002807 Permalink: /a/wake-sleep-algorithm