Hi guys, After Matt and Daniel suggested a tutorial, I felt that that NuStudio is not so intuitive like I thought. Yeah, play an existing example is very easy, but create a HTM from scratch involves know how the inputs are organized in the input files. Furthermore, create an encoder is other subject that doesn't involve only intuition, but know how NuStudio integrate sensors to HTMs.
This said, I create a issue for this demand: https://github.com/DavidRagazzi/nupic.studio/issues/8 I appreciate any feeback about. Cheers, David On 10 September 2014 13:35, Subutai Ahmad <[email protected]> wrote: > > Very nice David! It would be great if people try this out and give you > some good feedback. It could develop into a very useful tool for everyone. > > --Subutai > > > On Wed, Sep 10, 2014 at 4:57 AM, Marek Otahal <[email protected]> > wrote: > >> Wow David! >> this looks awesome! >> Can't wait to get home and play with it. >> KUDOS!! >> >> On Wed, Sep 10, 2014 at 1:51 PM, Joseph Skippings < >> [email protected]> wrote: >> >>> Wow that is awesome!!! >>> >>> Sent from my iPhone >>> >>> On Sep 10, 2014, at 7:20 AM, David Ragazzi <[email protected]> >>> wrote: >>> >>> Thank you, guys! >>> >>> > The connections visualisation looks like a great *explanatory tool* >>> too! >>> >>> This is other objective, I remember that Jeff Hawkins commented about >>> the need of tool that allow visualize a HTM in 3D to check what changed >>> along the time.. For this, NuStudio keeps the history of states (max=5, but >>> you can increase), so you might slide the "step bar" for check if the >>> columns are active at moment, were predicted or not, or if the input is >>> unexpected which cells were chosen as learning cells, or what new synapses >>> were created or removed, etc. >>> >>> > How difficult would it be for an intermediate developer to create a >>> similar application for Nupic.core c++? >>> >>> Daniel, you don't need re-invent the wheel, you could change NuStudio to >>> handle NuPIC C++ instead of NuPIC Python. It's because NuPIC Python dist >>> has some bindings to handle NuPIC C++. Theorically, you just need change >>> some "headers imports" and voilá.. But in the pratice, this is not >>> possible, because NuStudio uses the new TM (implemented on Python but not >>> on C++).. So I advise you wait a little until TM is implemented on C++.. >>> But once this done, a few changes will be need.. >>> >>> > another Ragazzi-quality production! >>> >>> Thanks for this, Fergal! :-D >>> >>> David >>> >>> On 10 September 2014 04:01, Fergal Byrne <[email protected]> >>> wrote: >>> >>>> Hi David, >>>> >>>> Wow, that looks and sounds like a great new addition to the NuPIC >>>> ecosystem. I'll have time to take a proper look at it this evening, but it >>>> already looks like you've pulled off yet another Ragazzi-quality >>>> production! Well done and thanks for sharing this - I think having great >>>> tools like this is hugely important for spreading the word about NuPIC and >>>> HTM. >>>> >>>> Cheers, >>>> >>>> Fergal Byrne >>>> >>>> On Wed, Sep 10, 2014 at 6:57 AM, Kevin Martin < >>>> [email protected]> wrote: >>>> >>>>> Awesome! One more cool thing to do when I get time. Great work! >>>>> >>>>> On Wed, Sep 10, 2014 at 11:08 AM, Ajay Ramanathan < >>>>> [email protected]> wrote: >>>>> >>>>>> It looks really cool; looking forward to it :D >>>>>> >>>>>> On Wed, Sep 10, 2014 at 9:48 AM, Michael Neale < >>>>>> [email protected]> wrote: >>>>>> >>>>>>> This looks incredible - what a great tool. The connections >>>>>>> visualisation looks like a great explanatory tool too! >>>>>>> >>>>>>> On Wed, Sep 10, 2014 at 9:39 AM, David Ragazzi < >>>>>>> [email protected]> wrote: >>>>>>> >>>>>>>> Hello NuPICers! >>>>>>>> >>>>>>>> Just for inform that in all these days I was out, I was creating an a >>>>>>>> tool that I believe will be a breakthrough for the community. This >>>>>>>> tool calls "NuPIC Studio", or just NuStudio. NuStudio is an >>>>>>>> all-in-one tool that allows users create a HTM neural network from >>>>>>>> scratch, train it, collect statistics, and share it among the members >>>>>>>> of >>>>>>>> the community. It is not just a visualization tool but an HTM builder, >>>>>>>> debugger and laboratory for experiments. It is ideal for newbies with >>>>>>>> little intimacy with NuPIC code as well as experts that wish a better >>>>>>>> productivity. Among its features and advantages I list: >>>>>>>> - Users can open, save, or change their "HTM projects" or of other >>>>>>>> developers. A typical project contains data to be trained, neural >>>>>>>> network >>>>>>>> configuration, statistics, etc, which can be shared to be analysed or >>>>>>>> integrated with other projects. >>>>>>>> - The HTM engine is the own original NuPIC libray (Python >>>>>>>> distribution). This means no port, no bindings, no re-implementation, >>>>>>>> etc. >>>>>>>> So any changes in the original nupic source can be immediatedly viewed. >>>>>>>> This helps users that wish test improvements like new encoders or even >>>>>>>> hierarchy, attention, and motor integration. >>>>>>>> - The project is pip-installable and for desktop use. >>>>>>>> >>>>>>>> Project details: >>>>>>>> - All code is implemented in Python. When I say "all code", I >>>>>>>> really mean that code like GUI, 3d simulation, etc, are writen in >>>>>>>> Python >>>>>>>> and use open-source and cross platform components. >>>>>>>> - All GUI stuff (forms, controls, etc) is implemented in PyQT. PyQT >>>>>>>> is the version of the famous QT adapted for python apps, which is >>>>>>>> open-source, cross-platform, complete, and very easy to code and >>>>>>>> change. >>>>>>>> - All utilities like XML serialization, canvas 2d, etc, also are >>>>>>>> implemented in PyQT. >>>>>>>> - A front-end object-oriented layer also written in Python is >>>>>>>> provided in order to ease the understanding of the NuPIC code and keep >>>>>>>> backwards compatibility. This means that someone with less experience >>>>>>>> in >>>>>>>> NuPIC could re-use this front-end in her projects. >>>>>>>> >>>>>>>> The project's site is: >>>>>>>> https://github.com/DavidRagazzi/nupic.studio >>>>>>>> >>>>>>>> and you can see some screen-shots attached to this message. >>>>>>>> >>>>>>>> Surely it still is not 100%, and it's expected that some >>>>>>>> installation issues arise, but I hope optimize the process as soon as >>>>>>>> possible. By the way, it works reasonably well and any people is >>>>>>>> welcome to >>>>>>>> try it or even improve it. >>>>>>>> >>>>>>>> I look forward for your feedback, it is very important! >>>>>>>> >>>>>>>> Cheers, >>>>>>>> David >>>>>>>> >>>>>>>> -- >>>>>>>> David Ragazzi >>>>>>>> MSc in Sofware Engineer (University of Liverpool) >>>>>>>> Try NuPIC Studio! https://github.com/DavidRagazzi/nupic.studio >>>>>>>> -- >>>>>>>> "I think James Connolly, the Irish revolutionary, is right when he >>>>>>>> says that the only prophets are those who make their future. So we're >>>>>>>> not anticipating, we're working for it." >>>>>>>> >>>>>>> >>>>>>> >>>>>>> >>>>>>> -- >>>>>>> Michael D Neale >>>>>>> home: www.michaelneale.net >>>>>>> blog: michaelneale.blogspot.com >>>>>>> >>>>>> >>>>>> >>>>> >>>> >>>> >>>> -- >>>> >>>> Fergal Byrne, Brenter IT >>>> >>>> http://inbits.com - Better Living through Thoughtful Technology >>>> http://ie.linkedin.com/in/fergbyrne/ - https://github.com/fergalbyrne >>>> >>>> Author, Real Machine Intelligence with Clortex and NuPIC >>>> Read for free or buy the book at https://leanpub.com/realsmartmachines >>>> >>>> Speaking on Clortex and HTM/CLA at euroClojure Krakow, June 2014: >>>> http://euroclojure.com/2014/ >>>> and at LambdaJam Chicago, July 2014: http://www.lambdajam.com >>>> >>>> e:[email protected] t:+353 83 4214179 >>>> Join the quest for Machine Intelligence at http://numenta.org >>>> Formerly of Adnet [email protected] http://www.adnet.ie >>>> >>> >>> >>> >>> -- >>> David Ragazzi >>> MSc in Sofware Engineer (University of Liverpool) >>> OS Community Commiter at Numenta.org >>> -- >>> "I think James Connolly, the Irish revolutionary, is right when he says that >>> the only prophets are those who make their future. So we're not >>> anticipating, we're working for it." >>> >>> >> >> >> -- >> Marek Otahal :o) >> > > -- David Ragazzi MSc in Sofware Engineer (University of Liverpool) OS Community Commiter at Numenta.org -- "I think James Connolly, the Irish revolutionary, is right when he says that the only prophets are those who make their future. So we're not anticipating , we're working for it."
