David, thanks for your answers.

My head is now full of questions. But it's time to start coding and testing!

> As an added note..

Then, it's time for someone else to get something done!!!

Thanks,
Takenori

On Sat, Oct 24, 2015 at 10:06 PM, cogmission (David Ray) <
[email protected]> wrote:

> Hi Takenori,
>
> Sounds good! Thanks for using HTM.java! Please remember to update to
> version v0.6.4-alpha as there have been some important updates (yesterday).
>
> 1. timestamp should be periodic?
>
>
> The timestamp can have gaps but not go backwards. It must be progressive,
> but not necessarily periodic.
>
>  2. one model for each node?
>
>
> Yes. "Model" in HTM.java's world means "Network". Operation of HTM.java is
> exactly the same as NuPIC in terms of its capability. So as far as I know,
> a separate model is needed for every predicted element. (I may be wrong
> about this - so if there are any doubts you should ask Matt Taylor (a.k.a.
> @rhyolight) or one of the other Numenta engineers.
>
> As an added note - I'm in the curious position of being an expert at
> knowing the code (both Python and Java), but I have very little experience
> actually using NuPIC to get things done... It's a symptom of being laser
> focused on code production - I haven't had time to actually use anything
> much. (Although that is slowly changing and I'm getting a bit of experience
> under my belt).
>
> Good luck with your project, and as always the NuPIC Community is willing
> to help!
>
> Cheers,
> David
>
> On Fri, Oct 23, 2015 at 10:00 PM, Takenori Sato <[email protected]>
> wrote:
>
>> Hi David,
>>
>> Your feedback is encouraging!
>>
>> Especially on a geographically distributed environment(e.g. cars as IoT
>> clients, and its backends for analytics), such an algorithm based on a
>> static threshold is not robust enough against various noises over data
>> centers.
>>
>> I expect HTM is very robust against such noises.
>>
>> OK, then I will use HTM for this subject, staring with embedding HTM.java
>> in Cassandra, and see how much it gets improved.
>>
>> Btw, I have some questions regarding the input format.
>>
>> 1. timestamp should be periodic?
>>
>> Should I give inputs periodically, at a fixed interval? Then, I need to
>> take an average response time(or max if not available) for a period.
>>
>> e.g.
>> timestamp(fixed interval), an average response time, node
>>
>> Or, can I simply feed as a health check response arrives?
>>
>> e.g.
>> timestamp(variable), response time, node
>>
>> 2. one model for each node?
>>
>> To get anomaly score for each node, do I need to have one model for each
>> node?
>>
>> Thanks,
>> Takenori
>>
>> On Fri, Oct 23, 2015 at 9:03 PM, cogmission (David Ray) <
>> [email protected]> wrote:
>>
>>> Hi Takenori,
>>>
>>> In my opinion (due to the constant time related pinging nature of the
>>> health checks), is YES :-) HTM is **perfect** for this...  Very interesting
>>> application of NuPIC technology, by the way!
>>>
>>> Cheers,
>>> David
>>>
>>> On Fri, Oct 23, 2015 at 2:13 AM, Takenori Sato <[email protected]>
>>> wrote:
>>>
>>>> Hello,
>>>>
>>>> In a distributed system, it is very important to know which node is
>>>> more healthier than others to make a request. Or of course, when to
>>>> determine one node should be treated as dead.
>>>>
>>>> For example, cassandra relies on phi accrual detector[1] to detect node
>>>> down. A node does a gossip communication with 3 nodes every second, and
>>>> exchanges information with each other. And its response time is used as an
>>>> input for the failure detection.
>>>>
>>>> Also, a badness score is computed with such information, and which is
>>>> used to choose a healthier node among replica nodes.
>>>>
>>>> But, I have seen many situations when it didn't work as expected,
>>>> especially choosing a healthier node.
>>>>
>>>> On the other hand, I know any service provider makes some kind of
>>>> health check request to detect if service is available or not. It may be
>>>> just a simple ping, or HEAD request.
>>>>
>>>> Then, I just wondered if it is a good use case to use HTM for failure
>>>> detection with such simple health check requests?
>>>>
>>>> For example, its input looks like this:
>>>>
>>>> time, node, avg response time(ms)
>>>> 10:00:00, node1, 10
>>>> 10:00:00, node2, 9
>>>> ...
>>>> 10:00:30, node1, 15
>>>> 10:00:30, node2, 10
>>>> ...
>>>>
>>>>
>>>> [1] http://www.jaist.ac.jp/~defago/files/pdf/IS_RR_2004_010.pdf
>>>>
>>>> Thanks,
>>>> Takenori
>>>>
>>>
>>>
>>>
>>> --
>>> *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
>>>
>>
>>
>
>
> --
> *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
>

Reply via email to