| Generating from a learned model |
| t-1 t |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| • | Keep the
previous hidden and |
||||||||||||||
| visible states
fixed |
|||||||||||||||
| – | They
provide a time- |
||||||||||||||
| dependent
bias for the |
|||||||||||||||
| hidden
units. |
|||||||||||||||
| • | Perform
alternating Gibbs |
||||||||||||||
| sampling for a
few iterations |
|||||||||||||||
| between the
hidden units and |
|||||||||||||||
| the most recent
visible units. |
|||||||||||||||
| – | This
picks new hidden and |
||||||||||||||
| visible
states that are |
|||||||||||||||
| compatible
with each other |
|||||||||||||||
| and
with the recent history. |
|||||||||||||||
| t-2 t-1 t |