I got to see this a bit before you completed it; and the finished product looks GREAT! This will be a wonderful contribution to the community - and make HTM Theory and its Tech much more accessible.
Great Job! On Sat, Apr 2, 2016 at 10:13 AM, Mika Schiller <[email protected]> wrote: > This is excellent Matt. I would have loved to see this when I started > getting into HTM and CLA a while back. It would also be great if at some > point you touch on how all this stuff differs from Deep Learning and other > approaches(and why it's better), as well as how it can apply to real world > applications and situations. Looking forward to seeing more. > > > On Friday, April 1, 2016, Matthew Taylor <[email protected]> wrote: > >> Hello NuPIC! >> >> https://www.youtube.com/watch?v=XMB0ri4qgwc >> >> HTM School is a new YouTube series I am producing to educate the >> general public about Hierarchical Temporal Memory. It is focused on >> the layperson, not the expert, so episodes will start off very basic >> and build up in complexity as the topical areas are populated. Each >> episode will be bite-sized at 10-15 minutes and dive into a particular >> topic of HTM theory. >> >> The plan is to progress through all the major concepts of HTM, >> including SDRs, spatial pooling, and temporal memory. If the series >> turns out to be popular, I’ll keep the episodes coming. If you want to >> see more, please like the video and subscribe to our YouTube channel! >> >> Stay tuned for the next episode, where I’ll talk about bit arrays. >> This will be an introduction to sparse distributed representations, >> the next topic in the series. I will probably do several episodes on >> SDRs! >> >> Regards, >> --------- >> Matt Taylor >> OS Community Flag-Bearer >> Numenta >> >> -- *With kind regards,* David Ray Java Solutions Architect *Cortical.io <http://cortical.io/>* Sponsor of: HTM.java <https://github.com/numenta/htm.java> [email protected] http://cortical.io
