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Although a little out of date now, Craig's blog gives a good idea of what NUPIC can and can't do, and how data issues (e.g. training set, variations in object appearance) affect the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Although a little out of date now, Craig's blog gives a good idea of what NUPIC can and can't do, and how data issues (e.g. training set, variations in object appearance) affect the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
Thanks for taking the time to discuss that, I feel strongly about this and so really like getting to know more on this kind of field. Do you mind updating your blog post with additional insight? It should be really useful for all of us.filme
ReplyDelete