data_mining:neural_network:rbm

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
data_mining:neural_network:rbm [2017/07/30 16:41] – phreazerdata_mining:neural_network:rbm [2017/07/30 16:59] (current) – [Restricted Boltzmann Machines] phreazer
Line 1: Line 1:
 ====== Restricted Boltzmann Machines ====== ====== Restricted Boltzmann Machines ======
  
-Boltzmann machine, with restriction, that neurons form a bipartite graph - pair of nodes from each of the visibile and hidden units have symmetric connections, but no connection between nodes in the group (e.g. connections between hidden units).+  * Boltzmann machine, with restriction, that neurons form a bipartite graph - pair of nodes from each of the visibile and hidden units have symmetric connections, but no connection between nodes in the group (e.g. connections between hidden units). 
 +  *  Shallow, two-layer structure 
 +  * Building block for deep belief nets  
 + 
 +  * Unsupervised learning 
 +    * Dim reduction 
 +    * No labels needed 
 +    * Autoencoder
  
 ===== Programming ===== ===== Programming =====
  • data_mining/neural_network/rbm.1501425717.txt.gz
  • Last modified: 2017/07/30 16:41
  • by phreazer