Cool! On Wed, Oct 15, 2014 at 9:24 AM, David Ragazzi <[email protected]> wrote:
> Ah I forgot to say: Don't worry if "Overview" don't give details about > this tool, in the "Simulation" chapter it is better explanned with an > example.. > > On 15 October 2014 11:14, David Ragazzi <[email protected]> wrote: > >> > From your answer, I see we're on the same page with the term "Region", >> but I wasn't sure that was what was being shown in the "Node Information" >> table (the leftmost column 'Region') ?? >> >> Ah yes... This page only shows the region's name and its precision rate >> (how many times the selected region predicts correctly).. It's onerous >> explain each page, so I focused only Columns page, wich shows information >> about all columns of the selected region. By the way, if you select a >> sensor in NodeSelector panel, you'll see tabs called "Sensor" and "Bits", >> not longer "Region", "Columns", etc.. ;-) >> >> On 15 October 2014 10:53, cogmission1 . <[email protected]> >> wrote: >> >>> David, >>> >>> I'm sorry I wrote that on the train and my finger slipped and the >>> message was sent! :) >>> >>> From your answer, I see we're on the same page with the term "Region", >>> but I wasn't sure that was what was being shown in the "Node Information" >>> table (the leftmost column 'Region') ?? >>> >>> >>> >>> On Wed, Oct 15, 2014 at 8:38 AM, David Ragazzi <[email protected]> >>> wrote: >>> >>>> Do you mean here? >>>> >>>> > A hierarchy is composed of regions and sensors: >>>> *>Region*: represented by a *trapezium*. Every Region must have at >>>> least one lower region or a Sensor to feed it input. >>>> *>Sensor*: represented by a *rectangle*. Its only role is feeding a >>>> region with acceptable inputs, i.e. a fixed array composed of 0's and 1's. >>>> Sensors collect input data from a file or a database. This data may be >>>> converted values (i.e. the array of 0's and 1's ready to be fed) or raw >>>> values (i.e. natural values like numbers, string, etc, which must be >>>> converted to an array using an *Encoder*). >>>> >>>> Well, cortical regions either receives input of lower regions or >>>> directly from sensors. It's important we don't confuse *sensor* with >>>> *sensory* region. The name *sensory *region is because they are those >>>> regions that handle biological sensors (all cortical regions located on >>>> parietal lobe), but they continue being cortical regions not sensors >>>> themselves. The non-sensory regions are those regions involved with >>>> planning, language, motor, etc, located in frontal lobe*. It's like V1 (a >>>> sensory region) receiving directly encoded input from optical nerve (a >>>> sensor). Or am I misunderstansding some neuroscience concept? :-/ >>>> >>>> >>>> On 15 October 2014 10:00, David Ray <[email protected]> wrote: >>>> >>>>> David, >>>>> >>>>> I'm curious about the use of the term region on this page: >>>>> https://github.com/nupic-community/nupic.studio/wiki/Overview >>>>> >>>>> ...where >>>>> Sent from my iPhone >>>>> >>>>> On Oct 15, 2014, at 6:55 AM, David Ragazzi <[email protected]> >>>>> wrote: >>>>> >>>>> I attached a screenshot where NodeInformation panel shows the current >>>>> value that was encoderd and fed into region and the respective likely >>>>> values (and their % probability) to appear in the next time step. >>>>> >>>>> Again, if you're having dificulties, don't hesitate on access the wiki >>>>> which is very complete and easy to follow: >>>>> https://github.com/nupic-community/nupic.studio/wiki >>>>> >>>>> On 14 October 2014 23:39, David Ragazzi <[email protected]> >>>>> wrote: >>>>> >>>>>> Hi guys, >>>>>> >>>>>> Finally I finished the encoders integration to NuPIC Studio!! Now you >>>>>> can create your projects using Numenta or your own encoders! >>>>>> >>>>>> To getting started, just check "counting" example to check how the >>>>>> famous (Numenta) Scalar Encoder works: Try change "counting_numbers.txt" >>>>>> input file with your own numbers and change the range by set the >>>>>> parameters >>>>>> of this encoder. Helpful link: >>>>>> https://github.com/numenta/nupic/wiki/Encoders >>>>>> >>>>>> Another good news: The NuPIC Studio wiki tutorial also is done! Just >>>>>> check it: >>>>>> >>>>>> https://github.com/nupic-community/nupic.studio/wiki >>>>>> >>>>>> Actually it was done some weeks ago, but I delayed its introduction >>>>>> to community because I'd like that encoders integration also was ok. >>>>>> Special thanks to David Ray and Fergal Byrne to review the wiki tutorial. >>>>>> >>>>>> Some other improvements: >>>>>> - Simulation was optimized: now it's faster because shows only cells >>>>>> with non-inactive state. >>>>>> - Refresh controls while run multiple steps. >>>>>> - Precision rate of the network. >>>>>> - Solved "Save Project" bug reported by Mike >>>>>> >>>>>> To get the new version with all these improvements, just use: >>>>>> >>>>>> (sudo) pip install nustudio >>>>>> >>>>>> The next weeks I'll concentrate my efforts in help all you to get >>>>>> started to NuPIC Studio including answer doubts, solve any bugs and >>>>>> improve >>>>>> documentation as well as finish the HotGym port to NuPIC Studio in order >>>>>> to >>>>>> Matt make the video tutorial. So please don't hesitate on give me >>>>>> feedback! >>>>>> >>>>>> -- >>>>>> 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." >>>>>> >>>>> >>>>> >>>>> >>>>> -- >>>>> 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." >>>>> >>>>> <encoded_values.png> >>>>> >>>>> >>>> >>>> >>>> -- >>>> 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." >>>> >>> >>> >>> >>> -- >>> *We find it hard to hear what another is saying because of how loudly >>> "who one is", speaks...* >>> >> >> >> >> -- >> 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." >> > > > > -- > 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." > -- *We find it hard to hear what another is saying because of how loudly "who one is", speaks...*
