A quick post here to give readers an idea of HTM/CLA performance on visual object recognition tasks.
Although a little out of date now, Craig's blog gives a good idea of what NUPIC can and can't do, and how data issues (e.g. training set, variations in object appearance) affect the results. This is a handy review for someone considering working with NUPIC:
http://www.craigquiter.com/post/16984424066/htm-notes
Although a little out of date now, Craig's blog gives a good idea of what NUPIC can and can't do, and how data issues (e.g. training set, variations in object appearance) affect the results. This is a handy review for someone considering working with NUPIC:
http://www.craigquiter.com/post/16984424066/htm-notes
