Subutai Ahmad
Subutai Ahmad
The file spatial_pooler.py contains two helper classes, CorticalColumns and BinaryCorticalColumns. These names are incorrect as these should refer to mini columns. There are also numerous references to cortical columns in...
There are a bunch of very confusing directories in `examples/opf/experiments` and `prediction/experiments`. They use old style OPF experiment running, are not well documented, and are pretty confusing. However some of...
This test fails occasionally when run with certain random seeds. Example output (including the seed that failed) is here: ``` ______________ SpatialPoolerCompatabilityTest.testCompatability2 _______________ [gw0] linux2 -- Python 2.7.5 /opt/numenta/anaconda/bin/python self...
The mechanism for adding synapses to a segment in temporal_memory has a subtle bug. When learning on a segment `self.maxNewSynapseCount - len(activeSynapses)` new synapses are added. This logic doesn't allow...
Clone of (now closed) NuPIC issue https://github.com/numenta/nupic/issues/894 As per https://github.com/numenta/nupic/issues/892, might be worth experimenting with the following approach: "Permanence values for shared inputs, which are input bits that are turned...
This is a cleaner way to train the network in phases.
Create simple vision experiment where we have a small number of images and small number of fixations. We want to see stable unique representations. This is mostly to test and...
This super issue plans workflow for speed optimizations by using a specialized library. Benefits: - SPEED! - fewer our-manually optimized (=hacked) code; cleanup - bugs/improvements delegated to lib's upstream -...
The method initPermConnected_() in the spatial pooler uses strange logic to initialize its permanence. It should probably initialize things uniformly: ``` Real SpatialPooler::initPermConnected_() { Real p = synPermConnected_ + (synPermMax_...