Matches in DBpedia 2016-04 for { ?s ?p "The wake-sleep algorithm is an unsupervised learning algorithm for a stochastic multilayer neural network. The algorithm adjusts the parameters so as to produce a good density estimator. There are two learning phases, the “wake” phase and the sleep “sleep” phase, which are performed alternately. It was first designed as a model for brain functioning using Variational Bayesian Learning. After that, the algorithm was adapted to machine learning."@en }
Showing triples 1 to 2 of
2
with 100 triples per page.
- Wake-sleep_algorithm comment "The wake-sleep algorithm is an unsupervised learning algorithm for a stochastic multilayer neural network. The algorithm adjusts the parameters so as to produce a good density estimator. There are two learning phases, the “wake” phase and the sleep “sleep” phase, which are performed alternately. It was first designed as a model for brain functioning using Variational Bayesian Learning. After that, the algorithm was adapted to machine learning.".
- Q7960888 comment "The wake-sleep algorithm is an unsupervised learning algorithm for a stochastic multilayer neural network. The algorithm adjusts the parameters so as to produce a good density estimator. There are two learning phases, the “wake” phase and the sleep “sleep” phase, which are performed alternately. It was first designed as a model for brain functioning using Variational Bayesian Learning. After that, the algorithm was adapted to machine learning.".