Closed breznak closed 4 years ago
FYI @steinroe this branch enables the old/new reintroduced param numActiveColumnsPerInhArea
.
Note: it needs the specific branch from htm.core.
See htm-community/NAB/pull/28. Still underperforms though. I would propose we try to
localAreaDensity
version as well as the numActiveColumnsPerInhArea
one to see if we can reach the NAB score numenta does.What do you think?
EDIT: Or maybe go back to check wether NAB is working correctly?
use the fake spatial anomaly detector Numenta used on both
yes, let's do that first. That way we're as close to numenta as possible.
numActiveCols
is not a silver bullet (atleast w/o any work) Should we merge this branch into fixing_...
? Both params can now be used.
Currently localAreaDensity > numActiveCols
I would propose to merge it and then creating a new branch for adding the fake spatial anomaly detector, as its probably easier to work with 2 branches instead of 4 when running the optimisations.
a new branch for adding the fake spatial anomaly detector
Let's add that just as a commit as well, fake spAnomaly can be controlled with a toggle in the detector
are you working on adding the fake spAnomaly? otherwise I would do it 👍
are you working on adding the fake spAnomaly? otherwise I would do it
please go ahead. for a couple of hours I'll need to do sth else
now the params are directly comparable to Numenta's.