MAKHFI.COM
Fascinating World of Neural Nets  
Neural Network Forums
Home PageHome Page : Neural Networks for Pattern Recognition : Restricted Boltzmann Machine in real-value data for training deep-neural network
  You are currently not logged in. You can view the forums, but cannot post messages. | HOME | Log In | Register | Search | Help
Post a Reply on This Topic Post a Reply on This Topic

Author Topic: Restricted Boltzmann Machine in real-value data for training deep-neural network
JasonChan Posted: 28-Dec-10 02:26
  Edit Edit
 
Email the Author Mail   View Author's Profile Profile  
Hello Everyone.

I am working on a project in which I apply the Restricted Boltzmann Machine to "pretrain" the autoencoder so that the initial weights are close to the optimal weights.


I find that the Restricted Boltzmann Machine just deal with the binary units,just like Hopfield Net, but if the input is real-value data(for example, 8-bit images), then do you know whether there is a good way to deal with this problem?


Thank you in advance
 

Post a Reply on This Topic Post a Reply on This Topic
 

Copyright © 2001-2003 Pejman Makhfi. All rights Reserved.