Live briefing
Everything about Wake-sleep algorithm
Unsupervised learning 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. Wikipedia →
🧠Start here: a 6-step reading path
- Read the overview: Wake-sleep algorithmA 5-minute orientation
- Skim a recent paper: A jerk-based algorithm ACCEL for the accurate classification of sleep–wake states from arm accelerationInfluential work since 2022
- Read the landmark paper: The "Wake-Sleep" Algorithm for Unsupervised Neural NetworksCited 617 times
- Go sideways: Helmholtz machineA closely related topic
- Go sideways: Unsupervised learningA closely related topic
đź“– Definitions
Noun A certain unsupervised learning algorithm for neural networks, having separate "wake" and "sleep" phases that attempt to connect the layers of neurons in alternating directions.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
The "Wake-Sleep" Algorithm for Unsupervised Neural Networks
A Novel Adaptive Wrist Actigraphy Algorithm for Sleep-Wake Assessment in Sleep Apnea Patients
Validity of an algorithm for determining sleep/wake states using a new actigraph
A novel machine learning unsupervised algorithm for sleep/wake identification using actigraphy
Performance evaluation of an automated single-channel sleep–wake detection algorithm
Newly developed waist actigraphy and its sleep/wake scoring algorithm
The Sleep Well Baby project: an automated real-time sleep–wake state prediction algorithm in preterm infants
An algorithm for actigraphy-based sleep/wake scoring: Comparison with polysomnography
🆕 Influential since 2022
A jerk-based algorithm ACCEL for the accurate classification of sleep–wake states from arm acceleration
Validity of a Novel Algorithm to Detect Bedtime, Wake Time, and Sleep Time in Adults
Personalized recognition of wake/sleep state based on the combined shapelets and K-means algorithm
Validating CircaCP: a generic sleep–wake cycle detection algorithm for unlabelled actigraphy data
Validity of an algorithm for determining sleep/wake states using FS-760 in school-aged children
đź“š Books worth reading
Open Library didn't respond; try again in a moment.
đź”— Related topics
- Helmholtz machine The Helmholtz machine (named after Hermann von Helmholtz and his concept of Helmholtz free energy) is a type of artificial neural network that can account…
- Unsupervised learning Unsupervised learning is a framework in machine learning where, in contrast to supervised learning, algorithms learn patterns exclusively from unlabeled…
- Representation learning In machine learning (ML), representation learning or feature learning is a set of techniques that allow a system to automatically discover the representations…
- Boltzmann machine A Boltzmann machine (also called Sherrington–Kirkpatrick model with external field or stochastic Ising model), named after Ludwig Boltzmann, is a spin-glass…
- Types of artificial neural networks Types of neural networks (NN) include a family of techniques. The simplest types have static components, including number of units, number of layers, unit…
- Deep learning In machine learning, deep learning (DL) focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representatio…
- Restricted Boltzmann machine A restricted Boltzmann machine (RBM) (also called a restricted Sherrington–Kirkpatrick model with external field or restricted stochastic Ising–Lenz–Little…
- Catastrophic interference Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously…