Don't worry about it I just wanted to get general idea ... I was
mostly interested of the Encoding internals. Alex Lavin gave me a
paper how it works, so I wrote what I needed for my experiments.

thanks again
PS> I have your github reference and saved it
-------| http://ifni.co


On Tue, Feb 23, 2016 at 8:18 PM, David Ray <[email protected]> wrote:
> Matt and I are going to take a look at it because some of the parameters are 
> off and the classifier predictions don't come out right - so give us a day or 
> so to work it out...
>
> Cheers,
> David
>
> Sent from my iPhone
>
>> On Feb 23, 2016, at 6:31 PM, mraptor <[email protected]> wrote:
>>
>> thanks alot
>> -------| http://ifni.co
>>
>>
>> On Tue, Feb 23, 2016 at 8:18 AM, cogmission (David Ray)
>> <[email protected]> wrote:
>>> @mraptor
>>>
>>> Here is the python version of a class named QuickTest.py. It demonstrates
>>> the connection of all the major algorithms (except Anomaly). This was
>>> written about a year ago, so forgive me if there are one or two tweaks
>>> necessary to make it compatible with the current NuPIC code? (Chances are
>>> that it is still compatible, but just in case - be forewarned).
>>>
>>> Maybe some enterprising Numenta engineer can take a look and make sure that
>>> the code is still relevant (then share the results again with the
>>> community)? This file seems to come in handy for new-comers and so may be
>>> useful as a tool to share?
>>>
>>> (see attached)
>>>
>>> Cheers,
>>> David
>>>
>>>> On Mon, Feb 22, 2016 at 10:29 PM, mraptor <[email protected]> wrote:
>>>>
>>>> that will be nice, if it is not too much of a hassle .
>>>> -------| http://ifni.co
>>>>
>>>>
>>>> On Mon, Feb 22, 2016 at 11:50 AM, cogmission (David Ray)
>>>> <[email protected]> wrote:
>>>>> If it helps, I also have an example Python file that shows the usage of
>>>>> each
>>>>> of the typical algorithms used in standalone fashion - in one quick easy
>>>>> file with an actual use-case? I can email it to you if you'd like?
>>>>>
>>>>> Cheers,
>>>>> David
>>>>>
>>>>> On Mon, Feb 22, 2016 at 10:24 AM, Matthew Taylor <[email protected]>
>>>>> wrote:
>>>>>>
>>>>>> Have you seen Scott's "Beginner's Guide"?
>>>>>>
>>>>>> https://github.com/numenta/nupic/wiki/Using-NuPIC#beginners-guide-to-nupic
>>>>>>
>>>>>> He instantiates the ScalarEncoder directly and uses it in a standalone
>>>>>> fashion. There is a link to the code too. Does that help?
>>>>>> ---------
>>>>>> Matt Taylor
>>>>>> OS Community Flag-Bearer
>>>>>> Numenta
>>>>>>
>>>>>>
>>>>>>> On Sat, Feb 20, 2016 at 10:36 PM, mraptor <[email protected]> wrote:
>>>>>>> thanks,
>>>>>>>
>>>>>>> I was talking mostly of standalone use i.e. separating it in its own
>>>>>>> class w/o any non-standard python dependencies
>>>>>>> -------| http://ifni.co
>>>>>>>
>>>>>>>
>>>>>>> On Sat, Feb 20, 2016 at 9:28 PM, Kentaro Iizuka
>>>>>>> <[email protected]> wrote:
>>>>>>>> Hello mraptor,
>>>>>>>>
>>>>>>>> Yes!
>>>>>>>> You can use NuPIC's ScalarEncoder as Python class.
>>>>>>>> NuPIC’s unit test code of ScalarEncoder may helpful for you.
>>>>>>>>
>>>>>>>>
>>>>>>>> https://github.com/numenta/nupic/blob/master/tests/unit/nupic/encoders/scalar_test.py
>>>>>>>>
>>>>>>>> Here is my small sample code using ScalarEncoder.
>>>>>>>> https://gist.github.com/iizukak/2c77e9e4ee8a842e86b7
>>>>>>>>
>>>>>>>> Best regards.
>>>>>>>>
>>>>>>>> 2016-02-21 5:01 GMT+09:00 mraptor <[email protected]>:
>>>>>>>>> hi,
>>>>>>>>>
>>>>>>>>> Is there a easy way to separate Scalar encoder as a standalone
>>>>>>>>> class.
>>>>>>>>> I only need init, encode/decode functionality.
>>>>>>>>>
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> https://github.com/numenta/nupic/blob/master/src/nupic/encoders/scalar.py
>>>>>>>>>
>>>>>>>>> I don't want to reinvent the wheel :)
>>>>>>>>>
>>>>>>>>> thanks
>>>>>>>>>
>>>>>>>>> -------| http://ifni.co
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> --
>>>>>>>> Kentaro Iizuka<[email protected]>
>>>>>>>>
>>>>>>>> Github
>>>>>>>> https://github.com/iizukak/
>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> With kind regards,
>>>>>
>>>>> David Ray
>>>>> Java Solutions Architect
>>>>>
>>>>> Cortical.io
>>>>> Sponsor of:  HTM.java
>>>>>
>>>>> [email protected]
>>>>> http://cortical.io
>>>
>>>
>>>
>>> --
>>> With kind regards,
>>>
>>> David Ray
>>> Java Solutions Architect
>>>
>>> Cortical.io
>>> Sponsor of:  HTM.java
>>>
>>> [email protected]
>>> http://cortical.io
>>
>

Reply via email to