Hi Wakan, Yes it is relevant apart from the TemporalPooler implementation which has since evolved (to become the TemporalMemory). The pseudocode specific to the TP is not the algorithm to be used going forward (though it is still in use, and produces adequate results - it is not the algorithm that will be used in the future HTM ecosystems).
For an understanding of what is happening outside of reading the code, I recommend the links I suggested above (the first being this one: Beginners HTM Theory Video <https://www.youtube.com/watch?v=z6r3ekreRzY>). Cheers, David On Sun, Jan 10, 2016 at 2:00 PM, Wakan Tanka <[email protected]> wrote: > Hello Cogmission, > White paper is few years old. Is it still relevant? Thank you. > > > On January 9, 2016 1:09:22 PM CET, "cogmission (David Ray)" < > [email protected]> wrote: >> >> Hi Kumari, >> >> This is the video I recommend after reading the CLA Whitepaper. This >> video to me fully describes the actual flow of data through the various >> algorithms - and is extremely helpful. Beginners HTM Theory Video >> <https://www.youtube.com/watch?v=z6r3ekreRzY> >> >> In addition, I have a blog here: http://cogmission.ai that has a >> collection of very useful links to all sorts of learning and community >> resources (check the top of the landing page). You may also find the blog >> itself to be an interesting resource. >> >> Cheers, >> David >> >> On Sat, Jan 9, 2016 at 12:48 AM, Joseph Rocca <[email protected]> >> wrote: >> >>> Welcome, Kumari! I found this video very helpful when I was starting >>> out: >>> http://numenta.com/learn/principles-of-hierarchical-temporal-memory.html >>> >>> There's also a bunch more on youtube. >>> >>> Cheers, >>> Joe >>> >>> On Sat, Jan 9, 2016 at 4:33 PM, Jonathan Mackenzie <[email protected]> >>> wrote: >>> >>>> What's your existing knowledge of machine learning? If you're just >>>> starting out, you might want to look into simpler models like SVM and >>>> simple neural networks. >>>> >>>> On 9 January 2016 at 14:01, Sebastián Narváez <[email protected]> >>>> wrote: >>>> >>>>> I think that the HTM Whitepaper is a very good tool to get a good >>>>> grasp on what Numenta and Nupic are about. >>>>> >>>>> http://numenta.com/learn/hierarchical-temporal-memory-white-paper.html >>>>> >>>>> On Thu, Jan 7, 2016 at 2:58 PM, Jeff Fohl <[email protected]> wrote: >>>>> >>>>>> Hello Kumari - >>>>>> >>>>>> This is probably the best place to start: >>>>>> https://github.com/numenta/nupic/wiki >>>>>> >>>>>> - Jeff >>>>>> >>>>>> On Thu, Jan 7, 2016 at 11:57 AM Kumari Shalini < >>>>>> [email protected]> wrote: >>>>>> >>>>>>> Hi, >>>>>>> >>>>>>> I'm a final year student and willing to learn machine learning using >>>>>>> numenta. I googled a lot but not able to find numenta docs properly. >>>>>>> So, please help me to get started or provide me some proper docs >>>>>>> links. >>>>>>> >>>>>>> -- >>>>>>> Kumari Shalini >>>>>>> >>>>>> >>>>> >>>> >>>> >>>> -- >>>> *Jonathan Mackenzie* >>>> BEng (Software) Hons >>>> PhD Candidate, Flinders University >>>> >>> >>> >> >> >> -- >> *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 >> > > -- > Sent from my Android device with K-9 Mail. Please excuse my brevity. > -- *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
