| Recursive Restricted Boltzmann Machines |
|
|
|
|
|
|
|
|
|
|
|
|
| • | First learn a
layer of |
||||||||||
| hidden features. |
|||||||||||
| • | Then treat the
feature |
||||||||||
| activations as
data |
|||||||||||
| and learn a
second |
|||||||||||
| layer of hidden |
|||||||||||
| features. |
|||||||||||
| • | And so on for as |
||||||||||
| many hidden
layers |
|||||||||||
| as we want. |
|||||||||||
| second layer of features |
| RBM2 |
|
|
| data is activities of |
|
| first layer of
features |
|
| first layer of features |
| RBM1 |
| data |