Deep Belief Network

Aller à : navigation, rechercher


Vocabulary Apprentissage profond


Termes privilégiés


Deep Belief Network (DBN)

DBNs are a type of probabilistic graphical model that learn a hierarchical representation of the data in an unsupervised manner. DBNs consist of multiple hidden layers with connections between neurons in each successive pair of layers. DBNs are built by stacking multiple RBNs on top of each other and training them one by one. • A fast learning algorithm for deep belief nets