Use a different set of locations for each object

Use a different set of locations for each object

Merge pull request #823 from mrcslws/improper-mashing
Latest feedback_sequences.py from @ThomasMiconi

Latest feedback_sequences.py from @ThomasMiconi
Fixes a bug in the collation of results for the "performance as a
function of noise" experiment which improperly mashed together most of
the data.

Latest feedback_sequences.py from @ThomasMiconi
Fixes a bug in the collation of results for the "performance as a
function of noise" experiment which improperly mashed together most of
the data.

Merge pull request #823 from mrcslws/improper-mashing
Latest feedback_sequences.py from @ThomasMiconi

Merge pull request #855 from mrcslws/continuous-attractor
Add Burak / Fiete continuous attractor code and visualization

Add Burak / Fiete continuous attractor code and visualization
I coded this for a blog post last year.
http://www.mrcslws.com/blocks/2017/04/16/grid-cells-CAN-model-visualized.html

I never really cleaned up the code -- it could definitely be faster,
especially the visualization code.

Add Burak / Fiete continuous attractor code and visualization
I coded this for a blog post last year.
http://www.mrcslws.com/blocks/2017/04/16/grid-cells-CAN-model-visualized.html

I never really cleaned up the code -- it could definitely be faster,
especially the visualization code.

Merge pull request #855 from mrcslws/continuous-attractor
Add Burak / Fiete continuous attractor code and visualization

Merge pull request #658 from mrcslws/SetMemory
Add "SetMemory_similar_objects" notebook

Merge pull request #659 from mrcslws/SetMemory
Add diagrams to SetMemory notebook

Merge pull request #661 from mrcslws/SetMemory
Update SetMemory diagrams

Add diagrams

Some Column Pooler tests were not testing the proximal connections
Because we weren't performing a reset after learning, some column
pooler tests would pass even if no proximal connections were formed.
If they just kept the previous active cells active, they would pass.
In some cases, this is what was happening (because the proximal
connections were below the connectedPermanence).

Update SetMemory diagrams

Merge pull request #665 from mrcslws/column-pooler-test-reset
Some Column Pooler tests weren't testing the proximal connections

Add "SetMemory_similar_objects" notebook

Bring back a 'compute' method for ColumnPooler

Merge pull request #655 from mrcslws/similar-objects
Re-add ColumnPooler "compute", add "similar objects" notebook

Update experiment to touch each object for 3 time steps

Update tests to use ColumnPooler's compute method

Add "similar objects" experiment notebook

Clarification

Fix a typo and an unused variable

Merge pull request #3383 from mrcslws/typo-cleanup
Fix a typo in TM, an unused variable in Connections

y-scaling: handle case where min == max
The y scale was broken when there was only one point on-screen.

Bring back a 'compute' method for ColumnPooler

Merge pull request #655 from mrcslws/similar-objects
Re-add ColumnPooler "compute", add "similar objects" notebook

Update experiment to touch each object for 3 time steps

Update tests to use ColumnPooler's compute method

Add "similar objects" experiment notebook

Clarification

Fix a typo and an unused variable

Merge pull request #3383 from mrcslws/typo-cleanup
Fix a typo in TM, an unused variable in Connections