| --- Log opened Tue Jan 31 00:00:19 2012 | ||
| CIA-11 | shogun: Sergey Lisitsyn master * re92461c / src/shogun/converter/KernelLocallyLinearEmbedding.cpp : Removed junk - http://git.io/pkx_wA | 00:01 |
|---|---|---|
| CIA-11 | shogun: Sergey Lisitsyn master * rff2eba8 / applications/edrt/swissroll_embedding.py : unParallel swissroll example - http://git.io/DrnSaA | 00:10 |
| CIA-11 | shogun: Sergey Lisitsyn master * rc36dfbc / (11 files in 4 dirs): PTHREAD ifdefing - http://git.io/pHLmGw | 01:11 |
| -!- blackburn [~qdrgsm@188.122.239.116] has quit [Quit: Leaving.] | 01:41 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 05:36 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has quit [Quit: Leaving.] | 05:39 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 05:46 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 06:16 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 06:16 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 06:16 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 06:16 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 07:00 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 07:00 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 07:01 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 07:01 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 07:01 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 07:31 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has left #shogun [] | 07:37 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has joined #shogun | 07:49 | |
| -!- dfrx [~f-x@inet-hqmc06-o.oracle.com] has quit [Quit: Leaving.] | 11:41 | |
| -!- Ram108 [~amma@14.99.84.107] has joined #shogun | 14:54 | |
| CIA-11 | shogun: Soeren Sonnenburg master * r870172a / (14 files in 5 dirs): | 15:20 |
| CIA-11 | shogun: Merge pull request #360 from karlnapf/master | 15:20 |
| CIA-11 | shogun: introduced standard cross-validation splitting (+6 more commits...) - http://git.io/rQtO7g | 15:20 |
| -!- Ram108 [~amma@14.99.84.107] has quit [Ping timeout: 252 seconds] | 16:35 | |
| -!- Ram108 [~amma@14.96.44.215] has joined #shogun | 16:59 | |
| -!- blackburn [~qdrgsm@109.226.82.146] has joined #shogun | 17:09 | |
| -!- blackburn1 [~qdrgsm@109.226.86.116] has joined #shogun | 17:56 | |
| -!- blackburn [~qdrgsm@109.226.82.146] has quit [Ping timeout: 255 seconds] | 17:58 | |
| -!- blackburn1 [~qdrgsm@109.226.86.116] has quit [Ping timeout: 276 seconds] | 18:37 | |
| -!- blackburn [~qdrgsm@109.226.85.31] has joined #shogun | 18:39 | |
| -!- blackburn1 [~qdrgsm@188.122.228.60] has joined #shogun | 19:10 | |
| -!- blackburn [~qdrgsm@109.226.85.31] has quit [Ping timeout: 240 seconds] | 19:14 | |
| blackburn1 | sonney2k: around? | 19:24 |
| -!- blackburn1 is now known as blackburn | 19:24 | |
| blackburn | I guess I have to place snapshot on the wbsite for now? | 19:26 |
| -!- Ram108 [~amma@14.96.44.215] has quit [Ping timeout: 245 seconds] | 19:36 | |
| blackburn | meaow | 19:50 |
| -!- Ram108 [~amma@14.96.94.247] has joined #shogun | 19:56 | |
| -!- cwidmer [8ca3fe9d@gateway/web/freenode/ip.140.163.254.157] has joined #shogun | 20:13 | |
| -!- sonne|work [~sonnenbu@194.78.35.195] has quit [Ping timeout: 276 seconds] | 20:14 | |
| @sonney2k | blackburn, done | 20:18 |
| blackburn | sonney2k: done with snapshot? | 20:18 |
| @sonney2k | btw we have 2 new potential mentors | 20:18 |
| blackburn | who? | 20:18 |
| @sonney2k | one willing to mentor GP integration | 20:18 |
| @sonney2k | olivier stegle | 20:19 |
| blackburn | gaussian processes? | 20:19 |
| @sonney2k | and one for doing structured output framework | 20:19 |
| blackburn | nice! | 20:19 |
| @sonney2k | nico goernitz | 20:19 |
| blackburn | nico | 20:19 |
| @sonney2k | I don't think we should have more | 20:19 |
| blackburn | hmm he is from tuebingen too? | 20:19 |
| @sonney2k | berlin | 20:19 |
| @sonney2k | olivier is from tuebingen | 20:19 |
| blackburn | heh full of germans | 20:19 |
| blackburn | ok | 20:20 |
| -!- Ram108 [~amma@14.96.94.247] has quit [Quit: Ex-Chat] | 20:24 | |
| -!- sonne|work [~sonnenbu@194.78.35.195] has joined #shogun | 20:29 | |
| blackburn | sonney2k: http://mloss.org/software/view/372/ | 20:35 |
| @sonney2k | blackburn, you should make the description a list | 20:35 |
| blackburn | sonney2k: does it support html? | 20:36 |
| @sonney2k | and add pca / kpca | 20:36 |
| @sonney2k | no but markdown syntax | 20:36 |
| blackburn | sonney2k: how to describe unordered list with this syntax? | 20:36 |
| @sonney2k | google :) | 20:37 |
| @sonney2k | but IIRC | 20:37 |
| @sonney2k | - a | 20:37 |
| @sonney2k | - b | 20:37 |
| @sonney2k | :) | 20:37 |
| blackburn | yes | 20:37 |
| blackburn | sonney2k: okay thanks | 20:37 |
| blackburn | sonney2k: we got some doubts about our abstract | 20:37 |
| blackburn | sonney2k: could you please judge it? :) | 20:37 |
| blackburn | there is a double SHOGUN referring | 20:38 |
| @sonney2k | blackburn, btw double affiiliations won't work with jmlr | 20:39 |
| @sonney2k | tell that to chris | 20:39 |
| @sonney2k | he can only use one | 20:39 |
| blackburn | cwidmer: ^ | 20:39 |
| @sonney2k | and the other as footnote | 20:39 |
| @sonney2k | blackburn, regarding abstract don't use SHOGUn twice | 20:40 |
| @sonney2k | just write with bindings | 20:40 |
| blackburn | We combine speed with ease of use, as our implementations are in C++, while providing bindings to other common languages such as Python, MATLAB, Octave, Java, Ruby, Lua, C\#. | 20:40 |
| blackburn | ? | 20:40 |
| blackburn | hm | 20:40 |
| blackburn | with bindings | 20:40 |
| blackburn | the problem is we can't say we wrote bindings :) | 20:41 |
| -!- f-x [~user@117.192.208.79] has joined #shogun | 20:43 | |
| @sonney2k | blackburn, you don't say that you wrote them - you only say these are provided | 20:50 |
| blackburn | so how to say it better | 20:50 |
| blackburn | with provided bndings? | 20:50 |
| @sonney2k | good as is | 20:50 |
| blackburn | ok | 20:50 |
| blackburn | thnaks | 20:50 |
| @sonney2k | no porblom | 20:51 |
| @sonney2k | scnr :D | 20:51 |
| blackburn | hah | 20:52 |
| f-x | blackburn, sonney2k, you guys here? hi everybody! | 20:54 |
| blackburn | f-x: hi, sure, we were talking :) | 20:55 |
| f-x | yeah hello there blackburn! :) been a while actually | 20:55 |
| @sonney2k | so f-x wassup? | 20:56 |
| f-x | hi sonney2k, been going through the exciting 1.1.0 over the last couple of days | 20:57 |
| f-x | not gone too deep yet, just doing it a bit slow. time management and all required a bit | 20:57 |
| blackburn | just like old times on #shogun | 20:59 |
| f-x | me being slow? :) yeah, it is! | 20:59 |
| f-x | actually was thinking of some short/medium-term plan which you guys might have | 20:59 |
| f-x | so i could get myself back on track a bit | 20:59 |
| f-x | anything, sonney2k, blackburn? | 21:00 |
| @sonney2k | f-x, well you could continue your vw / shogun interaction | 21:00 |
| blackburn | oh | 21:01 |
| f-x | sonney2k: that's the aim. thought i might need some kind of a familarity phase seeing the changes shogun has undergone | 21:01 |
| blackburn | well we have a lot of ideas.. | 21:01 |
| @sonney2k | f-x, none really in the online feature stuff | 21:01 |
| @sonney2k | f-x, so you as the author should easily be able to continue | 21:02 |
| f-x | ah alright then.. i'll think of some kind of road map | 21:02 |
| f-x | good to know, sonney2k | 21:02 |
| f-x | and blackburn you're welcome to suggest ideas in core shogun too if you need some help | 21:02 |
| @sonney2k | f-x, of course if you are looking for easy tasks you could aswell translate a new linear svm solver from octave to c++ :) | 21:03 |
| blackburn | f-x: yes I would formulate some if you need some tasks | 21:03 |
| f-x | sonney2k: sure, anything.. i want to have a brief spell so i know how to organize my time with work/shogun/other activities | 21:03 |
| blackburn | f-x: have you seen we -> to github issues? | 21:04 |
| f-x | go ahead, blackburn.. | 21:04 |
| f-x | and a nope to that question | 21:04 |
| @sonney2k | f-x, the newton svm for example http://www.shogun-toolbox.org/gsoc-ideas.html#newtonsvm | 21:04 |
| blackburn | you should check, we have wrote down some ideas (https://github.com/shogun-toolbox/shogun/issues?sort=created&direction=desc&state=open) | 21:04 |
| blackburn | too briefly but we can discuss | 21:05 |
| @sonney2k | f-x, it really depends on what you want to do | 21:05 |
| @sonney2k | we also need e.g. multiclass machines | 21:05 |
| @sonney2k | or some image related features | 21:05 |
| @sonney2k | (hog, ...) | 21:05 |
| blackburn | sonney2k: hey I do not like integrating hog here | 21:06 |
| @sonney2k | f-x, so if you have an application in mind or some preferences let us know | 21:06 |
| f-x | sonney2k: at this moment, mainly something to get used to the new 'style' of shogun, if it has changed recently | 21:06 |
| blackburn | sonney2k: we would end with doing our own OS :D | 21:07 |
| @sonney2k | f-x, style didn't change | 21:07 |
| f-x | eg. how we moved on to SGVector, SGMatrix etc.. things like that | 21:07 |
| f-x | and memory management, eg.SG_MALLOC | 21:07 |
| @sonney2k | f-x, we converted most of the code now | 21:07 |
| @sonney2k | to use SGVector/Matrix etc | 21:07 |
| @sonney2k | and everything uses SG_MALLOC | 21:07 |
| @sonney2k | but that's mostly it | 21:08 |
| f-x | nice.. i'll look at some code to get a feel of it.. and probably that SVM should be ok for starters | 21:08 |
| @sonney2k | some bigger changes requiring newer versions of swig / python that are not really user visible (but faster - hopefully more elegant) | 21:08 |
| @sonney2k | f-x, yeah that would certainly be an easy job | 21:09 |
| f-x | sonney2k, perfect | 21:09 |
| f-x | i'll get started on it tomorrow. good to have some kind of plan now.. thanks! | 21:09 |
| @sonney2k | np :) | 21:11 |
| @sonney2k | I am getting tired already *yawn* | 21:11 |
| blackburn | sonney2k: lets pray for my paper before going sleep :D | 21:11 |
| f-x | our prayers are with you, blackburn | 21:12 |
| f-x | and the issues page is so nice | 21:12 |
| blackburn | f-x: hah :) | 21:12 |
| blackburn | f-x: I'm trying to present my collection of algorithms as toolkit to JMLR mloss | 21:13 |
| f-x | blackburn, seriously amazing stuff | 21:13 |
| f-x | you have it more or less ready? | 21:13 |
| blackburn | f-x: what is ready? | 21:14 |
| f-x | the paper? | 21:14 |
| blackburn | ah yes | 21:14 |
| @sonney2k | ...~~~ooooOOOO~mighty~jmlr~editors~~~select~the~dumbest~ignorant~and~easiest~to~excite~reviewers~for~~~~ohh~our~dear~blackburn~~~OOOOoooooo~~~... | 21:14 |
| blackburn | I hope to submit it today | 21:14 |
| blackburn | :D | 21:14 |
| blackburn | I got afraid of the message above | 21:15 |
| f-x | looked like some weird map in nethack | 21:15 |
| * sonney2k is going to compose a song for blackburn named "praising the reviewers" | 21:15 | |
| blackburn | sonney2k: seriously I've read reviews for shogun mloss paper and it makes me think they would say 'who are you guy? what is that shit?' | 21:16 |
| f-x | i say you'd do just fine, anyway your efforts are really appreciable, blackburn | 21:17 |
| blackburn | hah I hope so | 21:17 |
| @sonney2k | blackburn, you will get a mixture of the above (reviewers) | 21:17 |
| @sonney2k | alright f-x, blackburn - nice meeting you again. time to sleep for me | 21:18 |
| @sonney2k | cu | 21:18 |
| blackburn | see you | 21:18 |
| f-x | see you sonney2k | 21:18 |
| blackburn | no idea what do you mean mixture of the above :) | 21:18 |
| f-x | your opinion and my opinion, i think he meant | 21:18 |
| blackburn | ah | 21:18 |
| f-x | mixed reviews :) | 21:18 |
| blackburn | would be nice to not having mixture of 'who fucking are you?' and 'what is the shit you present?' :D | 21:19 |
| blackburn | f-x: http://dl.dropbox.com/u/10139213/shogun/lisitsyn12a.pdf that's a current presubmit draft | 21:19 |
| f-x | hehe i'm sure they won't use those words _exactly_ :) | 21:19 |
| f-x | ooh lemme see | 21:19 |
| blackburn | ahha yeah sure | 21:19 |
| f-x | wow blackburn, did you meet cwidmer? | 21:20 |
| blackburn | f-x: not really, why I'd have to? | 21:20 |
| f-x | just curious | 21:20 |
| f-x | naah, just a question which struck me | 21:20 |
| blackburn | ah no | 21:20 |
| blackburn | I've never been abroad actually :D | 21:20 |
| f-x | blackburn, me neither :-/ | 21:21 |
| f-x | blackburn: nice page of edrt you have there | 21:23 |
| blackburn | ugly :) | 21:23 |
| f-x | looks like a proper research page :) | 21:23 |
| blackburn | f-x: btw feel free to do any remarks | 21:24 |
| blackburn | looks pretty raw for me still | 21:25 |
| f-x | blackburn, lack of energy and a dire lack of knowledge mean i can't make any comments regarding the content yet | 21:25 |
| f-x | but i actually thought the overall 'feel' is quite good | 21:25 |
| blackburn | :) I see, no problem | 21:25 |
| f-x | and btw blackburn, you know why we capitalize SHOGUN? does it stand for anything? | 21:26 |
| blackburn | f-x: Soeren + Gunnar | 21:26 |
| blackburn | no idea why SHO | 21:27 |
| blackburn | sounds better :) | 21:27 |
| f-x | Shoeren :) | 21:27 |
| f-x | yeah | 21:27 |
| blackburn | SH?GUN | 21:27 |
| blackburn | hah | 21:27 |
| f-x | good performance too, i see (edrt) | 21:28 |
| blackburn | well should be best | 21:29 |
| blackburn | but sklearn is too fast on toy data | 21:29 |
| blackburn | and matlab is going fast too on high-dim data | 21:29 |
| blackburn | well it will be faster later | 21:29 |
| f-x | but its terrible in isomap (sklearn) | 21:30 |
| blackburn | not really terrible | 21:30 |
| f-x | 2-3 times slower | 21:30 |
| f-x | oh i have to sleep now.. but looking good so far blackburn. all the best with it | 21:37 |
| blackburn | f-x: thanks! sleep well | 21:37 |
| f-x | see you | 21:38 |
| -!- f-x [~user@117.192.208.79] has quit [Quit: ERC Version 5.3 (IRC client for Emacs)] | 21:38 | |
| -!- cwidmer [8ca3fe9d@gateway/web/freenode/ip.140.163.254.157] has quit [Quit: Page closed] | 23:14 | |
| blackburn | SUBMITTED | 23:35 |
| --- Log closed Wed Feb 01 00:00:19 2012 | ||
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!