| 12 |
|
|
|
| Contrastive divergence learning: |
||
| A quick way to learn an RBM |
||
| j |
| j |
|
|
|
|
|
|
|
| Start with a
training vector on the |
||||||
| visible units. |
||||||
| Update all the
hidden units in |
||||||
| parallel |
||||||
| Update all the
visible units in |
||||||
| parallel to get a
“reconstruction”. |
||||||
| Update all the
hidden units again. |
||||||
| i |
| i |
| reconstruction |
| data |
|
|
| This is
not following the gradient of the log likelihood. But it works well. |
|
| It is
approximately following the gradient of another objective function. |
|