| An RBM with real-valued visible units |
|
|
|
|
|
|
|
|
|
| • | Using Gaussian
visible |
|||||||
| units we can get
much |
||||||||
| sharper
predictions and |
||||||||
| alternating Gibbs |
||||||||
| sampling is still
easy, |
||||||||
| though learning
is |
||||||||
| slower. |
||||||||
|
|
|
| energy-gradient |
||
| produced
by the total |
||
| input
to a visible unit |
||
|
|
|
| parabolic |
||
| containment |
||
| function |
||
|
|
| Welling
et. al. (2005) show how to extend RBM’s to the |
|
| exponential
family. See also Bengio et. al. 2007) |
|