You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@spark.apache.org by Gowtham N <go...@gmail.com> on 2013/08/15 21:32:35 UTC
ML Algos
Hi,
Can someone give details about the future work in ML algorithms (Inside
mllib folder).
Currently there are some basic algorithms implemented. Is there any roadmap
regarding what ML algorithms are required?
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
SVMs and Perceptrons are indeed similar. Nonetheless, people still use
Perceptrons, so adding it would provide more options for people, and
implementing Perceptrons would be a good way to get hands-on experience
with the codebase.
On Sun, Sep 8, 2013 at 4:37 PM, Gowtham N <go...@gmail.com> wrote:
> Yes, I am interested.
>
> Since SVM is already there why do we need perceptrons? Will it be used
> later with neural networks?
>
>
>
> On Sun, Sep 8, 2013 at 10:27 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
>> What about the perception algorithm? If you're interested in working on
>> that, I can add a JIRA ticket and assign it to you.
>>
>>
>>
>> On Sun, Sep 8, 2013 at 10:03 AM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Hi, Is there any option in Classification, Recommendation or Clustering?
>>>
>>>
>>>
>>> On Sat, Sep 7, 2013 at 11:13 AM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>>> This is one option: https://spark-project.atlassian.net/browse/MLI-4.
>>>> We can talk offline if you're interested.
>>>>
>>>>
>>>> On Sat, Sep 7, 2013 at 12:34 AM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>>> Any algo which is not yet started? :)
>>>>> PCA?
>>>>>
>>>>>
>>>>> On Friday, September 6, 2013, Ameet Talwalkar wrote:
>>>>>
>>>>>> I should note that once our plans firm up a bit, I will add a ticket
>>>>>> with these details.
>>>>>>
>>>>>>
>>>>>> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <
>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>
>>>>>> Hi Rohit,
>>>>>>
>>>>>> I didn't add a ticket b/c our work right now is pretty exploratory,
>>>>>> and hence I don't have much concrete to share.
>>>>>>
>>>>>> -Ameet
>>>>>>
>>>>>>
>>>>>> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com>wrote:
>>>>>>
>>>>>> Hi Ameet,
>>>>>>
>>>>>> Is there a ticket for ANN work? We are also in early stages of
>>>>>> implementing the same.
>>>>>>
>>>>>> Regards,
>>>>>> Rohit
>>>>>>
>>>>>>
>>>>>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <
>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>
>>>>>> Dear Gowtham,
>>>>>>
>>>>>> Yes, this work is in early stages but has already started.
>>>>>>
>>>>>> -Ameet
>>>>>>
>>>>>>
>>>>>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>>
>>>>>> Ameet, Thanks for all the info in JIRA.
>>>>>> I wanted to know if Neural Networks is already started?
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>
>>>>>> Ah OK -- you sent your earlier email just after I added the decision
>>>>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>>>>> confusion!
>>>>>>
>>>>>>
>>>>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <gowtham.n.mail@gmail.com
>>>>>> > wrote:
>>>>>>
>>>>>> Oh, ok. I was looking only at only MLlib.
>>>>>>
>>>>>>
>>>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>>>
>>>>>> Hi Gowtham,
>>>>>>
>>>>>> As you have probably noticed, I am in the process of updating the
>>>>>> JIRA issues for MLI, including an entry for decision trees (I will continue
>>>>>> to add more items over the next few weeks). @manishamde and @hirakendu have
>>>>>> taken the lead on the decision tree implementation and have made good
>>>>>> progress so far, but it's a bit too early to put a specific date on its
>>>>>> release.
>>>>>>
>>>>>> -Ameet
>>>>>>
>>>>>>
>>>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>>
>>>>>> Ameet, What about Decision Trees? I heard that its almost done too
>>>>>> and will be released soon?
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>
>>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>>> an announcement once I have done so.
>>>>>>
>>>>>> <https://spark-project.atlassian.net/browse/MLLIB>
>>>>>>
>>>>>>
>>>>>
>>>>> --
>>>>> Gowtham Natarajan
>>>>>
>>>>
>>>>
>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Yes, I am interested.
Since SVM is already there why do we need perceptrons? Will it be used
later with neural networks?
On Sun, Sep 8, 2013 at 10:27 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> What about the perception algorithm? If you're interested in working on
> that, I can add a JIRA ticket and assign it to you.
>
>
>
> On Sun, Sep 8, 2013 at 10:03 AM, Gowtham N <go...@gmail.com>wrote:
>
>> Hi, Is there any option in Classification, Recommendation or Clustering?
>>
>>
>>
>> On Sat, Sep 7, 2013 at 11:13 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu
>> > wrote:
>>
>>> This is one option: https://spark-project.atlassian.net/browse/MLI-4.
>>> We can talk offline if you're interested.
>>>
>>>
>>> On Sat, Sep 7, 2013 at 12:34 AM, Gowtham N <go...@gmail.com>wrote:
>>>
>>>> Any algo which is not yet started? :)
>>>> PCA?
>>>>
>>>>
>>>> On Friday, September 6, 2013, Ameet Talwalkar wrote:
>>>>
>>>>> I should note that once our plans firm up a bit, I will add a ticket
>>>>> with these details.
>>>>>
>>>>>
>>>>> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <
>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>
>>>>> Hi Rohit,
>>>>>
>>>>> I didn't add a ticket b/c our work right now is pretty exploratory,
>>>>> and hence I don't have much concrete to share.
>>>>>
>>>>> -Ameet
>>>>>
>>>>>
>>>>> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>>>>>
>>>>> Hi Ameet,
>>>>>
>>>>> Is there a ticket for ANN work? We are also in early stages of
>>>>> implementing the same.
>>>>>
>>>>> Regards,
>>>>> Rohit
>>>>>
>>>>>
>>>>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <
>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>
>>>>> Dear Gowtham,
>>>>>
>>>>> Yes, this work is in early stages but has already started.
>>>>>
>>>>> -Ameet
>>>>>
>>>>>
>>>>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>> Ameet, Thanks for all the info in JIRA.
>>>>> I wanted to know if Neural Networks is already started?
>>>>>
>>>>>
>>>>>
>>>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>
>>>>> Ah OK -- you sent your earlier email just after I added the decision
>>>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>>>> confusion!
>>>>>
>>>>>
>>>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>> Oh, ok. I was looking only at only MLlib.
>>>>>
>>>>>
>>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>>
>>>>> Hi Gowtham,
>>>>>
>>>>> As you have probably noticed, I am in the process of updating the JIRA
>>>>> issues for MLI, including an entry for decision trees (I will continue to
>>>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>>>> taken the lead on the decision tree implementation and have made good
>>>>> progress so far, but it's a bit too early to put a specific date on its
>>>>> release.
>>>>>
>>>>> -Ameet
>>>>>
>>>>>
>>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>>>> will be released soon?
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>
>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>> an announcement once I have done so.
>>>>>
>>>>> <https://spark-project.atlassian.net/browse/MLLIB>
>>>>>
>>>>>
>>>>
>>>> --
>>>> Gowtham Natarajan
>>>>
>>>
>>>
>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
What about the perception algorithm? If you're interested in working on
that, I can add a JIRA ticket and assign it to you.
On Sun, Sep 8, 2013 at 10:03 AM, Gowtham N <go...@gmail.com> wrote:
> Hi, Is there any option in Classification, Recommendation or Clustering?
>
>
>
> On Sat, Sep 7, 2013 at 11:13 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
>> This is one option: https://spark-project.atlassian.net/browse/MLI-4.
>> We can talk offline if you're interested.
>>
>>
>> On Sat, Sep 7, 2013 at 12:34 AM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Any algo which is not yet started? :)
>>> PCA?
>>>
>>>
>>> On Friday, September 6, 2013, Ameet Talwalkar wrote:
>>>
>>>> I should note that once our plans firm up a bit, I will add a ticket
>>>> with these details.
>>>>
>>>>
>>>> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>> Hi Rohit,
>>>>
>>>> I didn't add a ticket b/c our work right now is pretty exploratory, and
>>>> hence I don't have much concrete to share.
>>>>
>>>> -Ameet
>>>>
>>>>
>>>> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>>>>
>>>> Hi Ameet,
>>>>
>>>> Is there a ticket for ANN work? We are also in early stages of
>>>> implementing the same.
>>>>
>>>> Regards,
>>>> Rohit
>>>>
>>>>
>>>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>> Dear Gowtham,
>>>>
>>>> Yes, this work is in early stages but has already started.
>>>>
>>>> -Ameet
>>>>
>>>>
>>>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>> Ameet, Thanks for all the info in JIRA.
>>>> I wanted to know if Neural Networks is already started?
>>>>
>>>>
>>>>
>>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>> Ah OK -- you sent your earlier email just after I added the decision
>>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>>> confusion!
>>>>
>>>>
>>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>> Oh, ok. I was looking only at only MLlib.
>>>>
>>>>
>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>
>>>> Hi Gowtham,
>>>>
>>>> As you have probably noticed, I am in the process of updating the JIRA
>>>> issues for MLI, including an entry for decision trees (I will continue to
>>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>>> taken the lead on the decision tree implementation and have made good
>>>> progress so far, but it's a bit too early to put a specific date on its
>>>> release.
>>>>
>>>> -Ameet
>>>>
>>>>
>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>>> will be released soon?
>>>>
>>>>
>>>>
>>>>
>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>>>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>>>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>>>> case of MLI), but I plan to update them this week and will send out an
>>>> announcement once I have done so.
>>>>
>>>> <https://spark-project.atlassian.net/browse/MLLIB>
>>>>
>>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Hi, Is there any option in Classification, Recommendation or Clustering?
On Sat, Sep 7, 2013 at 11:13 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> This is one option: https://spark-project.atlassian.net/browse/MLI-4. We
> can talk offline if you're interested.
>
>
> On Sat, Sep 7, 2013 at 12:34 AM, Gowtham N <go...@gmail.com>wrote:
>
>> Any algo which is not yet started? :)
>> PCA?
>>
>>
>> On Friday, September 6, 2013, Ameet Talwalkar wrote:
>>
>>> I should note that once our plans firm up a bit, I will add a ticket
>>> with these details.
>>>
>>>
>>> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>> Hi Rohit,
>>>
>>> I didn't add a ticket b/c our work right now is pretty exploratory, and
>>> hence I don't have much concrete to share.
>>>
>>> -Ameet
>>>
>>>
>>> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>>>
>>> Hi Ameet,
>>>
>>> Is there a ticket for ANN work? We are also in early stages of
>>> implementing the same.
>>>
>>> Regards,
>>> Rohit
>>>
>>>
>>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu
>>> > wrote:
>>>
>>> Dear Gowtham,
>>>
>>> Yes, this work is in early stages but has already started.
>>>
>>> -Ameet
>>>
>>>
>>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>>
>>> Ameet, Thanks for all the info in JIRA.
>>> I wanted to know if Neural Networks is already started?
>>>
>>>
>>>
>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>> Ah OK -- you sent your earlier email just after I added the decision
>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>> confusion!
>>>
>>>
>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>
>>> Oh, ok. I was looking only at only MLlib.
>>>
>>>
>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>
>>> Hi Gowtham,
>>>
>>> As you have probably noticed, I am in the process of updating the JIRA
>>> issues for MLI, including an entry for decision trees (I will continue to
>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>> taken the lead on the decision tree implementation and have made good
>>> progress so far, but it's a bit too early to put a specific date on its
>>> release.
>>>
>>> -Ameet
>>>
>>>
>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>
>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>> will be released soon?
>>>
>>>
>>>
>>>
>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>>> case of MLI), but I plan to update them this week and will send out an
>>> announcement once I have done so.
>>>
>>> <https://spark-project.atlassian.net/browse/MLLIB>
>>>
>>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
This is one option: https://spark-project.atlassian.net/browse/MLI-4. We
can talk offline if you're interested.
On Sat, Sep 7, 2013 at 12:34 AM, Gowtham N <go...@gmail.com> wrote:
> Any algo which is not yet started? :)
> PCA?
>
>
> On Friday, September 6, 2013, Ameet Talwalkar wrote:
>
>> I should note that once our plans firm up a bit, I will add a ticket with
>> these details.
>>
>>
>> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <ameet@eecs.berkeley.edu
>> > wrote:
>>
>> Hi Rohit,
>>
>> I didn't add a ticket b/c our work right now is pretty exploratory, and
>> hence I don't have much concrete to share.
>>
>> -Ameet
>>
>>
>> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>>
>> Hi Ameet,
>>
>> Is there a ticket for ANN work? We are also in early stages of
>> implementing the same.
>>
>> Regards,
>> Rohit
>>
>>
>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>>
>> Dear Gowtham,
>>
>> Yes, this work is in early stages but has already started.
>>
>> -Ameet
>>
>>
>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>
>> Ameet, Thanks for all the info in JIRA.
>> I wanted to know if Neural Networks is already started?
>>
>>
>>
>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>> ameet@eecs.berkeley.edu> wrote:
>>
>> Ah OK -- you sent your earlier email just after I added the decision tree
>> issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>> confusion!
>>
>>
>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>
>> Oh, ok. I was looking only at only MLlib.
>>
>>
>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>
>> Hi Gowtham,
>>
>> As you have probably noticed, I am in the process of updating the JIRA
>> issues for MLI, including an entry for decision trees (I will continue to
>> add more items over the next few weeks). @manishamde and @hirakendu have
>> taken the lead on the decision tree implementation and have made good
>> progress so far, but it's a bit too early to put a specific date on its
>> release.
>>
>> -Ameet
>>
>>
>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>
>> Ameet, What about Decision Trees? I heard that its almost done too and
>> will be released soon?
>>
>>
>>
>>
>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <ameet@eecs.berkeley.edu
>> > wrote:
>>
>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>> case of MLI), but I plan to update them this week and will send out an
>> announcement once I have done so.
>>
>> <https://spark-project.atlassian.net/browse/MLLIB>
>>
>>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Any algo which is not yet started? :)
PCA?
On Friday, September 6, 2013, Ameet Talwalkar wrote:
> I should note that once our plans firm up a bit, I will add a ticket with
> these details.
>
>
> On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
> Hi Rohit,
>
> I didn't add a ticket b/c our work right now is pretty exploratory, and
> hence I don't have much concrete to share.
>
> -Ameet
>
>
> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>
> Hi Ameet,
>
> Is there a ticket for ANN work? We are also in early stages of
> implementing the same.
>
> Regards,
> Rohit
>
>
> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
> Dear Gowtham,
>
> Yes, this work is in early stages but has already started.
>
> -Ameet
>
>
> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>
> Ameet, Thanks for all the info in JIRA.
> I wanted to know if Neural Networks is already started?
>
>
>
> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu
> > wrote:
>
> Ah OK -- you sent your earlier email just after I added the decision tree
> issue on the MLI JIRA, so I assumed you had read it. Sorry for the
> confusion!
>
>
> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>
> Oh, ok. I was looking only at only MLlib.
>
>
> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>
> Hi Gowtham,
>
> As you have probably noticed, I am in the process of updating the JIRA
> issues for MLI, including an entry for decision trees (I will continue to
> add more items over the next few weeks). @manishamde and @hirakendu have
> taken the lead on the decision tree implementation and have made good
> progress so far, but it's a bit too early to put a specific date on its
> release.
>
> -Ameet
>
>
> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>
> Ameet, What about Decision Trees? I heard that its almost done too and
> will be released soon?
>
>
>
>
> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
> Yes, JIRA is intended to serve this purpose, and we need to do a better
> job moving forward of using JIRA to communicate our roadmap. The JIRA
> pages for MLlib and MLI are currently very sparsely populated (empty in the
> case of MLI), but I plan to update them this week and will send out an
> announcement once I have done so.
>
> <https://spark-project.atlassian.net/browse/MLLIB>
>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
I should note that once our plans firm up a bit, I will add a ticket with
these details.
On Fri, Sep 6, 2013 at 10:18 PM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> Hi Rohit,
>
> I didn't add a ticket b/c our work right now is pretty exploratory, and
> hence I don't have much concrete to share.
>
> -Ameet
>
>
> On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
>
>> Hi Ameet,
>>
>> Is there a ticket for ANN work? We are also in early stages of
>> implementing the same.
>>
>> Regards,
>> Rohit
>>
>>
>> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>>
>>> Dear Gowtham,
>>>
>>> Yes, this work is in early stages but has already started.
>>>
>>> -Ameet
>>>
>>>
>>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>>
>>>> Ameet, Thanks for all the info in JIRA.
>>>> I wanted to know if Neural Networks is already started?
>>>>
>>>>
>>>>
>>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>>> Ah OK -- you sent your earlier email just after I added the decision
>>>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>>>> confusion!
>>>>>
>>>>>
>>>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>>> Oh, ok. I was looking only at only MLlib.
>>>>>>
>>>>>>
>>>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>>>
>>>>>>> Hi Gowtham,
>>>>>>>
>>>>>>> As you have probably noticed, I am in the process of updating the
>>>>>>> JIRA issues for MLI, including an entry for decision trees (I will continue
>>>>>>> to add more items over the next few weeks). @manishamde and @hirakendu have
>>>>>>> taken the lead on the decision tree implementation and have made good
>>>>>>> progress so far, but it's a bit too early to put a specific date on its
>>>>>>> release.
>>>>>>>
>>>>>>> -Ameet
>>>>>>>
>>>>>>>
>>>>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <gowtham.n.mail@gmail.com
>>>>>>> > wrote:
>>>>>>>
>>>>>>>> Ameet, What about Decision Trees? I heard that its almost done too
>>>>>>>> and will be released soon?
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>>>
>>>>>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>>>>>> an announcement once I have done so.
>>>>>>>>>
>>>>>>>>> spark-project.atlassian.net/browse/MLLIB
>>>>>>>>> spark-project.atlassian.net/browse/MLI
>>>>>>>>>
>>>>>>>>> -Ameet
>>>>>>>>>
>>>>>>>>>
>>>>>>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <
>>>>>>>>> gowtham.n.mail@gmail.com> wrote:
>>>>>>>>>
>>>>>>>>>> Ameet,
>>>>>>>>>>
>>>>>>>>>> Is there any bugzilla or any place where people tell about what
>>>>>>>>>> they are working on, so that there will be no duplication? I started
>>>>>>>>>> looking into neural nets, then realized that someone is already working on
>>>>>>>>>> it.
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>>
>>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> --
>>>>>>>> Gowtham Natarajan
>>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>
>>>>>> --
>>>>>> Gowtham Natarajan
>>>>>>
>>>>>
>>>>>
>>>>
>>>>
>>>> --
>>>> Gowtham Natarajan
>>>>
>>>
>>>
>>
>>
>> --
>>
>> ____________________________
>> www.tuplejump.com
>> *The Data Engineering Platform*
>>
>
>
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Hi Rohit,
I didn't add a ticket b/c our work right now is pretty exploratory, and
hence I don't have much concrete to share.
-Ameet
On Fri, Sep 6, 2013 at 8:58 PM, Rohit Rai <ro...@tuplejump.com> wrote:
> Hi Ameet,
>
> Is there a ticket for ANN work? We are also in early stages of
> implementing the same.
>
> Regards,
> Rohit
>
>
> On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
>> Dear Gowtham,
>>
>> Yes, this work is in early stages but has already started.
>>
>> -Ameet
>>
>>
>> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Ameet, Thanks for all the info in JIRA.
>>> I wanted to know if Neural Networks is already started?
>>>
>>>
>>>
>>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>>> Ah OK -- you sent your earlier email just after I added the decision
>>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>>> confusion!
>>>>
>>>>
>>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>>> Oh, ok. I was looking only at only MLlib.
>>>>>
>>>>>
>>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>>
>>>>>> Hi Gowtham,
>>>>>>
>>>>>> As you have probably noticed, I am in the process of updating the
>>>>>> JIRA issues for MLI, including an entry for decision trees (I will continue
>>>>>> to add more items over the next few weeks). @manishamde and @hirakendu have
>>>>>> taken the lead on the decision tree implementation and have made good
>>>>>> progress so far, but it's a bit too early to put a specific date on its
>>>>>> release.
>>>>>>
>>>>>> -Ameet
>>>>>>
>>>>>>
>>>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>>
>>>>>>> Ameet, What about Decision Trees? I heard that its almost done too
>>>>>>> and will be released soon?
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>>
>>>>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>>>>> an announcement once I have done so.
>>>>>>>>
>>>>>>>> spark-project.atlassian.net/browse/MLLIB
>>>>>>>> spark-project.atlassian.net/browse/MLI
>>>>>>>>
>>>>>>>> -Ameet
>>>>>>>>
>>>>>>>>
>>>>>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <
>>>>>>>> gowtham.n.mail@gmail.com> wrote:
>>>>>>>>
>>>>>>>>> Ameet,
>>>>>>>>>
>>>>>>>>> Is there any bugzilla or any place where people tell about what
>>>>>>>>> they are working on, so that there will be no duplication? I started
>>>>>>>>> looking into neural nets, then realized that someone is already working on
>>>>>>>>> it.
>>>>>>>>>
>>>>>>>>>
>>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> --
>>>>>>> Gowtham Natarajan
>>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>>> --
>>>>> Gowtham Natarajan
>>>>>
>>>>
>>>>
>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
>
> --
>
> ____________________________
> www.tuplejump.com
> *The Data Engineering Platform*
>
Re: ML Algos
Posted by Rohit Rai <ro...@tuplejump.com>.
Hi Ameet,
Is there a ticket for ANN work? We are also in early stages of implementing
the same.
Regards,
Rohit
On Sat, Sep 7, 2013 at 7:43 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> Dear Gowtham,
>
> Yes, this work is in early stages but has already started.
>
> -Ameet
>
>
> On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com>wrote:
>
>> Ameet, Thanks for all the info in JIRA.
>> I wanted to know if Neural Networks is already started?
>>
>>
>>
>> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <
>> ameet@eecs.berkeley.edu> wrote:
>>
>>> Ah OK -- you sent your earlier email just after I added the decision
>>> tree issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>>> confusion!
>>>
>>>
>>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>>
>>>> Oh, ok. I was looking only at only MLlib.
>>>>
>>>>
>>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>>
>>>>> Hi Gowtham,
>>>>>
>>>>> As you have probably noticed, I am in the process of updating the JIRA
>>>>> issues for MLI, including an entry for decision trees (I will continue to
>>>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>>>> taken the lead on the decision tree implementation and have made good
>>>>> progress so far, but it's a bit too early to put a specific date on its
>>>>> release.
>>>>>
>>>>> -Ameet
>>>>>
>>>>>
>>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>>> Ameet, What about Decision Trees? I heard that its almost done too
>>>>>> and will be released soon?
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>>
>>>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>>>> an announcement once I have done so.
>>>>>>>
>>>>>>> spark-project.atlassian.net/browse/MLLIB
>>>>>>> spark-project.atlassian.net/browse/MLI
>>>>>>>
>>>>>>> -Ameet
>>>>>>>
>>>>>>>
>>>>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <gowtham.n.mail@gmail.com
>>>>>>> > wrote:
>>>>>>>
>>>>>>>> Ameet,
>>>>>>>>
>>>>>>>> Is there any bugzilla or any place where people tell about what
>>>>>>>> they are working on, so that there will be no duplication? I started
>>>>>>>> looking into neural nets, then realized that someone is already working on
>>>>>>>> it.
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>
>>>>>>
>>>>>>
>>>>>> --
>>>>>> Gowtham Natarajan
>>>>>>
>>>>>
>>>>>
>>>>
>>>> --
>>>> Gowtham Natarajan
>>>>
>>>
>>>
>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
--
____________________________
www.tuplejump.com
*The Data Engineering Platform*
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Dear Gowtham,
Yes, this work is in early stages but has already started.
-Ameet
On Fri, Sep 6, 2013 at 3:30 PM, Gowtham N <go...@gmail.com> wrote:
> Ameet, Thanks for all the info in JIRA.
> I wanted to know if Neural Networks is already started?
>
>
>
> On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu
> > wrote:
>
>> Ah OK -- you sent your earlier email just after I added the decision tree
>> issue on the MLI JIRA, so I assumed you had read it. Sorry for the
>> confusion!
>>
>>
>> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Oh, ok. I was looking only at only MLlib.
>>>
>>>
>>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>>
>>>> Hi Gowtham,
>>>>
>>>> As you have probably noticed, I am in the process of updating the JIRA
>>>> issues for MLI, including an entry for decision trees (I will continue to
>>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>>> taken the lead on the decision tree implementation and have made good
>>>> progress so far, but it's a bit too early to put a specific date on its
>>>> release.
>>>>
>>>> -Ameet
>>>>
>>>>
>>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>>>> will be released soon?
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>>> ameet@eecs.berkeley.edu> wrote:
>>>>>
>>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>>> an announcement once I have done so.
>>>>>>
>>>>>> spark-project.atlassian.net/browse/MLLIB
>>>>>> spark-project.atlassian.net/browse/MLI
>>>>>>
>>>>>> -Ameet
>>>>>>
>>>>>>
>>>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>>
>>>>>>> Ameet,
>>>>>>>
>>>>>>> Is there any bugzilla or any place where people tell about what they
>>>>>>> are working on, so that there will be no duplication? I started looking
>>>>>>> into neural nets, then realized that someone is already working on it.
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>>
>>>>> --
>>>>> Gowtham Natarajan
>>>>>
>>>>
>>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Ameet, Thanks for all the info in JIRA.
I wanted to know if Neural Networks is already started?
On Mon, Aug 26, 2013 at 12:15 AM, Ameet Talwalkar
<am...@eecs.berkeley.edu>wrote:
> Ah OK -- you sent your earlier email just after I added the decision tree
> issue on the MLI JIRA, so I assumed you had read it. Sorry for the
> confusion!
>
>
> On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
>
>> Oh, ok. I was looking only at only MLlib.
>>
>>
>> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>>
>>> Hi Gowtham,
>>>
>>> As you have probably noticed, I am in the process of updating the JIRA
>>> issues for MLI, including an entry for decision trees (I will continue to
>>> add more items over the next few weeks). @manishamde and @hirakendu have
>>> taken the lead on the decision tree implementation and have made good
>>> progress so far, but it's a bit too early to put a specific date on its
>>> release.
>>>
>>> -Ameet
>>>
>>>
>>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>>
>>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>>> will be released soon?
>>>>
>>>>
>>>>
>>>>
>>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>>> Yes, JIRA is intended to serve this purpose, and we need to do a
>>>>> better job moving forward of using JIRA to communicate our roadmap. The
>>>>> JIRA pages for MLlib and MLI are currently very sparsely populated (empty
>>>>> in the case of MLI), but I plan to update them this week and will send out
>>>>> an announcement once I have done so.
>>>>>
>>>>> spark-project.atlassian.net/browse/MLLIB
>>>>> spark-project.atlassian.net/browse/MLI
>>>>>
>>>>> -Ameet
>>>>>
>>>>>
>>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>>> Ameet,
>>>>>>
>>>>>> Is there any bugzilla or any place where people tell about what they
>>>>>> are working on, so that there will be no duplication? I started looking
>>>>>> into neural nets, then realized that someone is already working on it.
>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>>
>>>>
>>>> --
>>>> Gowtham Natarajan
>>>>
>>>
>>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Ah OK -- you sent your earlier email just after I added the decision tree
issue on the MLI JIRA, so I assumed you had read it. Sorry for the
confusion!
On Mon, Aug 26, 2013 at 12:05 AM, Gowtham N <go...@gmail.com>wrote:
> Oh, ok. I was looking only at only MLlib.
>
>
> On Monday, August 26, 2013, Ameet Talwalkar wrote:
>
>> Hi Gowtham,
>>
>> As you have probably noticed, I am in the process of updating the JIRA
>> issues for MLI, including an entry for decision trees (I will continue to
>> add more items over the next few weeks). @manishamde and @hirakendu have
>> taken the lead on the decision tree implementation and have made good
>> progress so far, but it's a bit too early to put a specific date on its
>> release.
>>
>> -Ameet
>>
>>
>> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Ameet, What about Decision Trees? I heard that its almost done too and
>>> will be released soon?
>>>
>>>
>>>
>>>
>>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>>>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>>>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>>>> case of MLI), but I plan to update them this week and will send out an
>>>> announcement once I have done so.
>>>>
>>>> spark-project.atlassian.net/browse/MLLIB
>>>> spark-project.atlassian.net/browse/MLI
>>>>
>>>> -Ameet
>>>>
>>>>
>>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>>> Ameet,
>>>>>
>>>>> Is there any bugzilla or any place where people tell about what they
>>>>> are working on, so that there will be no duplication? I started looking
>>>>> into neural nets, then realized that someone is already working on it.
>>>>>
>>>>>
>>>>>
>>>>
>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Oh, ok. I was looking only at only MLlib.
On Monday, August 26, 2013, Ameet Talwalkar wrote:
> Hi Gowtham,
>
> As you have probably noticed, I am in the process of updating the JIRA
> issues for MLI, including an entry for decision trees (I will continue to
> add more items over the next few weeks). @manishamde and @hirakendu have
> taken the lead on the decision tree implementation and have made good
> progress so far, but it's a bit too early to put a specific date on its
> release.
>
> -Ameet
>
>
> On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <gowtham.n.mail@gmail.com<javascript:_e({}, 'cvml', 'gowtham.n.mail@gmail.com');>
> > wrote:
>
>> Ameet, What about Decision Trees? I heard that its almost done too and
>> will be released soon?
>>
>>
>>
>>
>> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <ameet@eecs.berkeley.edu<javascript:_e({}, 'cvml', 'ameet@eecs.berkeley.edu');>
>> > wrote:
>>
>>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>>> case of MLI), but I plan to update them this week and will send out an
>>> announcement once I have done so.
>>>
>>> spark-project.atlassian.net/browse/MLLIB
>>> spark-project.atlassian.net/browse/MLI
>>>
>>> -Ameet
>>>
>>>
>>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <gowtham.n.mail@gmail.com<javascript:_e({}, 'cvml', 'gowtham.n.mail@gmail.com');>
>>> > wrote:
>>>
>>>> Ameet,
>>>>
>>>> Is there any bugzilla or any place where people tell about what they
>>>> are working on, so that there will be no duplication? I started looking
>>>> into neural nets, then realized that someone is already working on it.
>>>>
>>>>
>>>>
>>>
>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Hi Gowtham,
As you have probably noticed, I am in the process of updating the JIRA
issues for MLI, including an entry for decision trees (I will continue to
add more items over the next few weeks). @manishamde and @hirakendu have
taken the lead on the decision tree implementation and have made good
progress so far, but it's a bit too early to put a specific date on its
release.
-Ameet
On Sun, Aug 25, 2013 at 6:13 PM, Gowtham N <go...@gmail.com> wrote:
> Ameet, What about Decision Trees? I heard that its almost done too and
> will be released soon?
>
>
>
>
> On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
>> Yes, JIRA is intended to serve this purpose, and we need to do a better
>> job moving forward of using JIRA to communicate our roadmap. The JIRA
>> pages for MLlib and MLI are currently very sparsely populated (empty in the
>> case of MLI), but I plan to update them this week and will send out an
>> announcement once I have done so.
>>
>> spark-project.atlassian.net/browse/MLLIB
>> spark-project.atlassian.net/browse/MLI
>>
>> -Ameet
>>
>>
>> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Ameet,
>>>
>>> Is there any bugzilla or any place where people tell about what they are
>>> working on, so that there will be no duplication? I started looking into
>>> neural nets, then realized that someone is already working on it.
>>>
>>>
>>>
>>
>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Ameet, What about Decision Trees? I heard that its almost done too and will
be released soon?
On Sat, Aug 17, 2013 at 3:49 PM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> Yes, JIRA is intended to serve this purpose, and we need to do a better
> job moving forward of using JIRA to communicate our roadmap. The JIRA
> pages for MLlib and MLI are currently very sparsely populated (empty in the
> case of MLI), but I plan to update them this week and will send out an
> announcement once I have done so.
>
> spark-project.atlassian.net/browse/MLLIB
> spark-project.atlassian.net/browse/MLI
>
> -Ameet
>
>
> On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com>wrote:
>
>> Ameet,
>>
>> Is there any bugzilla or any place where people tell about what they are
>> working on, so that there will be no duplication? I started looking into
>> neural nets, then realized that someone is already working on it.
>>
>>
>>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Yes, JIRA is intended to serve this purpose, and we need to do a better job
moving forward of using JIRA to communicate our roadmap. The JIRA pages
for MLlib and MLI are currently very sparsely populated (empty in the case
of MLI), but I plan to update them this week and will send out an
announcement once I have done so.
spark-project.atlassian.net/browse/MLLIB
spark-project.atlassian.net/browse/MLI
-Ameet
On Sat, Aug 17, 2013 at 2:37 PM, Gowtham N <go...@gmail.com> wrote:
> Ameet,
>
> Is there any bugzilla or any place where people tell about what they are
> working on, so that there will be no duplication? I started looking into
> neural nets, then realized that someone is already working on it.
>
>
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Ameet,
Is there any bugzilla or any place where people tell about what they are
working on, so that there will be no duplication? I started looking into
neural nets, then realized that someone is already working on it.
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
PMML is not on our near-term roadmap. That being said, we'd welcome
contributions that extend our system to support it.
On Sat, Aug 17, 2013 at 12:32 PM, Paco Nathan <ce...@gmail.com> wrote:
> +1 ADMM
>
> Also, in terms of commercial adoption, is support for PMML on the roadmap?
>
>
>
> On Sat, Aug 17, 2013 at 11:41 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu
> > wrote:
>
>> Thanks for the clarification! Yes, we aim to add ADMM to MLI in the
>> upcoming months.
>>
>>
>> On Sat, Aug 17, 2013 at 11:34 AM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Yes. It is the Stanford optimization algorithm.
>>>
>>>
>>> On Saturday, August 17, 2013, Nat wrote:
>>>
>>>> Hi,
>>>>
>>>> I am tempted to think it is from
>>>> http://www.stanford.edu/~boyd/papers/pdf/admm_slides.pdf
>>>>
>>>>
>>>> On Sat, Aug 17, 2013 at 10:26 AM, Ameet Talwalkar <
>>>> ameet@eecs.berkeley.edu> wrote:
>>>>
>>>>> Our upcoming release will include the Alternating Least Squares
>>>>> algorithm for Collaborative filtering. There are of course several other
>>>>> techniques for CF (e.g., SGD-based, trace-norm, neighborhood methods,
>>>>> divide-and-conquer approaches, etc.), and we hope that some of these
>>>>> methods will be added, with initial implementations facilitated by the
>>>>> high-level abstractions provided by the MLI.
>>>>>
>>>>> We are looking into adding neural network functionality (as noted in
>>>>> my previous email).
>>>>>
>>>>> Could you explain what you mean by "ADM" -- I'm not familiar with that
>>>>> acronym?
>>>>>
>>>>>
>>>>> On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>>>
>>>>>> Is anyone working on neural networks, ADM, Collaborative Filtering
>>>>>> etc?
>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>> --
>>> Gowtham Natarajan
>>>
>>
>>
>
Re: ML Algos
Posted by Paco Nathan <ce...@gmail.com>.
+1 ADMM
Also, in terms of commercial adoption, is support for PMML on the roadmap?
On Sat, Aug 17, 2013 at 11:41 AM, Ameet Talwalkar
<am...@eecs.berkeley.edu>wrote:
> Thanks for the clarification! Yes, we aim to add ADMM to MLI in the
> upcoming months.
>
>
> On Sat, Aug 17, 2013 at 11:34 AM, Gowtham N <go...@gmail.com>wrote:
>
>> Yes. It is the Stanford optimization algorithm.
>>
>>
>> On Saturday, August 17, 2013, Nat wrote:
>>
>>> Hi,
>>>
>>> I am tempted to think it is from
>>> http://www.stanford.edu/~boyd/papers/pdf/admm_slides.pdf
>>>
>>>
>>> On Sat, Aug 17, 2013 at 10:26 AM, Ameet Talwalkar <
>>> ameet@eecs.berkeley.edu> wrote:
>>>
>>>> Our upcoming release will include the Alternating Least Squares
>>>> algorithm for Collaborative filtering. There are of course several other
>>>> techniques for CF (e.g., SGD-based, trace-norm, neighborhood methods,
>>>> divide-and-conquer approaches, etc.), and we hope that some of these
>>>> methods will be added, with initial implementations facilitated by the
>>>> high-level abstractions provided by the MLI.
>>>>
>>>> We are looking into adding neural network functionality (as noted in my
>>>> previous email).
>>>>
>>>> Could you explain what you mean by "ADM" -- I'm not familiar with that
>>>> acronym?
>>>>
>>>>
>>>> On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>>
>>>>> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>>>>>
>>>>>
>>>>
>>>
>>
>> --
>> Gowtham Natarajan
>>
>
>
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Thanks for the clarification! Yes, we aim to add ADMM to MLI in the
upcoming months.
On Sat, Aug 17, 2013 at 11:34 AM, Gowtham N <go...@gmail.com>wrote:
> Yes. It is the Stanford optimization algorithm.
>
>
> On Saturday, August 17, 2013, Nat wrote:
>
>> Hi,
>>
>> I am tempted to think it is from
>> http://www.stanford.edu/~boyd/papers/pdf/admm_slides.pdf
>>
>>
>> On Sat, Aug 17, 2013 at 10:26 AM, Ameet Talwalkar <
>> ameet@eecs.berkeley.edu> wrote:
>>
>>> Our upcoming release will include the Alternating Least Squares
>>> algorithm for Collaborative filtering. There are of course several other
>>> techniques for CF (e.g., SGD-based, trace-norm, neighborhood methods,
>>> divide-and-conquer approaches, etc.), and we hope that some of these
>>> methods will be added, with initial implementations facilitated by the
>>> high-level abstractions provided by the MLI.
>>>
>>> We are looking into adding neural network functionality (as noted in my
>>> previous email).
>>>
>>> Could you explain what you mean by "ADM" -- I'm not familiar with that
>>> acronym?
>>>
>>>
>>> On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <go...@gmail.com>wrote:
>>>
>>>> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>>>>
>>>>
>>>
>>
>
> --
> Gowtham Natarajan
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Yes. It is the Stanford optimization algorithm.
On Saturday, August 17, 2013, Nat wrote:
> Hi,
>
> I am tempted to think it is from
> http://www.stanford.edu/~boyd/papers/pdf/admm_slides.pdf
>
>
> On Sat, Aug 17, 2013 at 10:26 AM, Ameet Talwalkar <ameet@eecs.berkeley.edu<javascript:_e({}, 'cvml', 'ameet@eecs.berkeley.edu');>
> > wrote:
>
>> Our upcoming release will include the Alternating Least Squares algorithm
>> for Collaborative filtering. There are of course several other techniques
>> for CF (e.g., SGD-based, trace-norm, neighborhood methods,
>> divide-and-conquer approaches, etc.), and we hope that some of these
>> methods will be added, with initial implementations facilitated by the
>> high-level abstractions provided by the MLI.
>>
>> We are looking into adding neural network functionality (as noted in my
>> previous email).
>>
>> Could you explain what you mean by "ADM" -- I'm not familiar with that
>> acronym?
>>
>>
>> On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <gowtham.n.mail@gmail.com<javascript:_e({}, 'cvml', 'gowtham.n.mail@gmail.com');>
>> > wrote:
>>
>>> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>>>
>>>
>>
>
--
Gowtham Natarajan
Re: ML Algos
Posted by Nat <re...@gmail.com>.
Hi,
I am tempted to think it is from
http://www.stanford.edu/~boyd/papers/pdf/admm_slides.pdf
On Sat, Aug 17, 2013 at 10:26 AM, Ameet Talwalkar
<am...@eecs.berkeley.edu>wrote:
> Our upcoming release will include the Alternating Least Squares algorithm
> for Collaborative filtering. There are of course several other techniques
> for CF (e.g., SGD-based, trace-norm, neighborhood methods,
> divide-and-conquer approaches, etc.), and we hope that some of these
> methods will be added, with initial implementations facilitated by the
> high-level abstractions provided by the MLI.
>
> We are looking into adding neural network functionality (as noted in my
> previous email).
>
> Could you explain what you mean by "ADM" -- I'm not familiar with that
> acronym?
>
>
> On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <go...@gmail.com>wrote:
>
>> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>>
>>
>
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Our upcoming release will include the Alternating Least Squares algorithm
for Collaborative filtering. There are of course several other techniques
for CF (e.g., SGD-based, trace-norm, neighborhood methods,
divide-and-conquer approaches, etc.), and we hope that some of these
methods will be added, with initial implementations facilitated by the
high-level abstractions provided by the MLI.
We are looking into adding neural network functionality (as noted in my
previous email).
Could you explain what you mean by "ADM" -- I'm not familiar with that
acronym?
On Fri, Aug 16, 2013 at 7:37 PM, Gowtham N <go...@gmail.com> wrote:
> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>
>
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Google's deep learning architecture is indeed quite interesting. Neither
MLlib nor MLI currently includes all of the components of this
architecture, but we intend to extend MLI in the upcoming months to contain
similar functionality.
On Fri, Aug 16, 2013 at 9:51 PM, Lijie Xu <cs...@gmail.com> wrote:
> Thanks for your quick reply. I like the new features. There is another
> related question about distributed ML.
> How do you think about the architecutre of Google's deep learning (
> http://www.cs.toronto.edu/~ranzato/publications/DistBeliefNIPS2012_withAppendix.pdf)?
> It contains parameter server, model replicas and data shards. Does MLBase
> have similar components?
>
>
> On Sat, Aug 17, 2013 at 10:37 AM, Gowtham N <go...@gmail.com>wrote:
>
>> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>>
>>
>
Re: ML Algos
Posted by Lijie Xu <cs...@gmail.com>.
Thanks for your quick reply. I like the new features. There is another
related question about distributed ML.
How do you think about the architecutre of Google's deep learning (
http://www.cs.toronto.edu/~ranzato/publications/DistBeliefNIPS2012_withAppendix.pdf)?
It contains parameter server, model replicas and data shards. Does MLBase
have similar components?
On Sat, Aug 17, 2013 at 10:37 AM, Gowtham N <go...@gmail.com>wrote:
> Is anyone working on neural networks, ADM, Collaborative Filtering etc?
>
>
Re: ML Algos
Posted by Gowtham N <go...@gmail.com>.
Is anyone working on neural networks, ADM, Collaborative Filtering etc?
Re: ML Algos
Posted by Matei Zaharia <ma...@gmail.com>.
On Aug 15, 2013, at 7:13 PM, Lijie Xu <cs...@gmail.com> wrote:
> 3) MLBase may require Spark to provide some new features for implementing some specific algorithms. Is there any? Or you have added some new fundamental features which are not supported in Spark-0.7?
On this particular aspect, we actually have a few small changes in 0.8 that are required in MLlib -- one is an improvement to the semantics of takeSample to allow over-sampling an RDD, and one is exposing each RDD's storage level as a public API so we can check whether it's cached and warn you otherwise. So it would be better to run this over 0.8 than 0.7. That said, you might be able to port many algorithms back to 0.7.
The plan is to release 0.8 this month, so it won't be too far away.
Matei
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
Thanks for your email -- I've responded inline.
On Thu, Aug 15, 2013 at 7:13 PM, Lijie Xu <cs...@gmail.com> wrote:
> Quite interesting. I have some questions about this amazing project:
> 1) In "Logistic Regression -‐ Weak Scaling", MLlib and VW run slower in
> each processor for fixed problem while data/machines are increasing. Could
> you explain which component causes this performance degradataion problem.
> Synchronization, network traffic, data partition or etc. ?
>
This is a good question, and to be honest, we still need to investigate
this further to get a better understanding of what's going on here.
> 2) What's the relationship between MLBase and GraphX?
>
Right now the two projects are being developed separately. As of now
MLbase does not support graph-based functionality, though moving forward,
it would be quite interesting to extend the MLI to include graph-based
primitives and leverage GraphX as a runtime.
>
> 3) MLBase may require Spark to provide some new features for implementing
> some specific algorithms. Is there any? Or you have added some new
> fundamental features which are not supported in Spark-0.7?
>
As MLbase is a relatively new project, we have been developing MLlib and
MLI to be compatible with Spark-0.8.
>
> On Fri, Aug 16, 2013 at 4:01 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
>
>> The following slides<http://files.meetup.com/3138542/sparkmeetup_8_6_13_final_reduced.pdf> summarize
>> the ML algorithms to be included in MLlib (slide 49) and MLI (slide 107) in
>> the near future. We plan to include additional
>> classification/regression/CF/clustering/optimization primitives over time
>> with the help of the open-source community, and based on feedback from
>> users about desired functionality. Moreover, we ultimately aim to add
>> advance ML functionality, as briefly described in slide 140.
>>
>> -Ameet
>>
>>
>> On Thu, Aug 15, 2013 at 12:32 PM, Gowtham N <go...@gmail.com>wrote:
>>
>>> Hi,
>>>
>>> Can someone give details about the future work in ML algorithms (Inside
>>> mllib folder).
>>> Currently there are some basic algorithms implemented. Is there any
>>> roadmap regarding what ML algorithms are required?
>>>
>>
>>
>
Re: ML Algos
Posted by Lijie Xu <cs...@gmail.com>.
Quite interesting. I have some questions about this amazing project:
1) In "Logistic Regression -‐ Weak Scaling", MLlib and VW run slower in
each processor for fixed problem while data/machines are increasing. Could
you explain which component causes this performance degradataion problem.
Synchronization, network traffic, data partition or etc. ?
2) What's the relationship between MLBase and GraphX?
3) MLBase may require Spark to provide some new features for implementing
some specific algorithms. Is there any? Or you have added some new
fundamental features which are not supported in Spark-0.7?
On Fri, Aug 16, 2013 at 4:01 AM, Ameet Talwalkar <am...@eecs.berkeley.edu>wrote:
> The following slides<http://files.meetup.com/3138542/sparkmeetup_8_6_13_final_reduced.pdf> summarize
> the ML algorithms to be included in MLlib (slide 49) and MLI (slide 107) in
> the near future. We plan to include additional
> classification/regression/CF/clustering/optimization primitives over time
> with the help of the open-source community, and based on feedback from
> users about desired functionality. Moreover, we ultimately aim to add
> advance ML functionality, as briefly described in slide 140.
>
> -Ameet
>
>
> On Thu, Aug 15, 2013 at 12:32 PM, Gowtham N <go...@gmail.com>wrote:
>
>> Hi,
>>
>> Can someone give details about the future work in ML algorithms (Inside
>> mllib folder).
>> Currently there are some basic algorithms implemented. Is there any
>> roadmap regarding what ML algorithms are required?
>>
>
>
Re: ML Algos
Posted by Ameet Talwalkar <am...@eecs.berkeley.edu>.
The following slides<http://files.meetup.com/3138542/sparkmeetup_8_6_13_final_reduced.pdf>
summarize
the ML algorithms to be included in MLlib (slide 49) and MLI (slide 107) in
the near future. We plan to include additional
classification/regression/CF/clustering/optimization primitives over time
with the help of the open-source community, and based on feedback from
users about desired functionality. Moreover, we ultimately aim to add
advance ML functionality, as briefly described in slide 140.
-Ameet
On Thu, Aug 15, 2013 at 12:32 PM, Gowtham N <go...@gmail.com>wrote:
> Hi,
>
> Can someone give details about the future work in ML algorithms (Inside
> mllib folder).
> Currently there are some basic algorithms implemented. Is there any
> roadmap regarding what ML algorithms are required?
>