|
|
|
|
|
| Do the 30-D codes found by the |
||||
| autoencoder preserve the class |
||||
| structure of the data? |
||||
|
|
|
|
|
| • | Take the activity
patterns in the top layer and |
|||
| display them in
2-D using a new form of non- |
||||
| linear
multidimensional scaling. |
||||
| • | Will the learning
find the natural classes? |
|||