|
|
|
|
|
| Using conditional higher-order Boltzmann |
||||
| machines to model image transformations |
||||
| (Memisevic and Hinton, 2007) |
||||
|
|
|
|
|
|
| • | A transformation
unit specifies which pixel goes |
||||
| to which other
pixel. |
|||||
| • | Conversely, each
pair of similar intensity pixels, |
||||
| one in each
image, votes for all the compatible |
|||||
| transformation
units. |
|||||
| image transformation |
| image(t) |
| image(t+1) |
