-
Notifications
You must be signed in to change notification settings - Fork 0
Spatial Pooler
See the CLA white paper for information on the spatial pooler.
For vision problems, the columns are laid out regularly in a 2D grid and each column as a square radius of inputs that it is connected to. Specifying an input border would result in the input bits on the exterior of the grid to not be included in the potential pools (which in the domain of vision is also referred to as receptive fields). For example, specifying an input border of '1' would result in the bits labeled '*' in the illustration below to be excluded. ******************** @@@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@@@@@@ ********************
There was an option added to reduce the amount that a column's connection to an input bit is incremented if the input bit is shared with other active columns.
| When | What |
|---|---|
| ??? | Spatial Pooler Memorization (aka "high tier") was added to increase learning speed. TODO: describe this |
| ??? | Reconstruction |
| ??? | Cloning |
| ??? | Option to increment shared active input bits less than non-shared |
| Early | Orphan columns added |
| Early | Input border added |
| Early | Topology added for vision |