| --- Log opened Mon Apr 16 00:00:19 2012 | ||
| -!- karlnapf [~heiko@host86-180-222-171.range86-180.btcentralplus.com] has joined #shogun | 00:04 | |
| -!- harshit_ [~harshit@182.68.246.67] has quit [Read error: Connection reset by peer] | 00:05 | |
| -!- av3ngr [av3ngr@nat/redhat/x-ujqsetgbcmptahsn] has joined #shogun | 01:15 | |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Ping timeout: 245 seconds] | 02:56 | |
| -!- karlnapf [~heiko@host86-180-222-171.range86-180.btcentralplus.com] has left #shogun [] | 03:08 | |
| -!- vikram360 [~vikram360@117.192.175.234] has joined #shogun | 04:20 | |
| -!- vikram360 [~vikram360@117.192.175.234] has quit [Ping timeout: 245 seconds] | 07:15 | |
| -!- vikram360 [~vikram360@117.192.175.234] has joined #shogun | 07:25 | |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 07:57 | |
| n4nd0 | good morning | 07:58 |
|---|---|---|
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 08:11 | |
| CIA-64 | shogun: Soeren Sonnenburg master * r1be6198 / (2 files): | 08:22 |
| CIA-64 | shogun: Merge pull request #446 from PhilippeTillet/nearest_centroid | 08:22 |
| CIA-64 | shogun: Added doxygen comments - http://git.io/yUFwRA | 08:22 |
| CIA-64 | shogun: Philippe Tillet master * r3255541 / (2 files): Added doxygen comments - http://git.io/L0IMDg | 08:22 |
| CIA-64 | shogun: Philippe Tillet master * r0dc55d2 / (2 files): Added assertion on feature type, removed store_model_features - http://git.io/z-feJA | 08:22 |
| -!- gsomix [~gsomix@188.168.128.177] has quit [Ping timeout: 252 seconds] | 08:24 | |
| -!- sonne|work [~sonnenbu@194.78.35.195] has joined #shogun | 08:48 | |
| -!- uricamic [9320543b@gateway/web/freenode/ip.147.32.84.59] has joined #shogun | 09:19 | |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 09:42 | |
| shogun-buildbot | build #480 of python_modular is complete: Success [build successful] Build details are at http://www.shogun-toolbox.org/buildbot/builders/python_modular/builds/480 | 09:51 |
| n4nd0 | shogun-buildbot: good job | 09:57 |
| -!- wiking [~wiking@78-23-189-112.access.telenet.be] has joined #shogun | 10:00 | |
| -!- wiking [~wiking@78-23-189-112.access.telenet.be] has quit [Changing host] | 10:00 | |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 10:00 | |
| -!- blackburn [5bdfb203@gateway/web/freenode/ip.91.223.178.3] has joined #shogun | 10:00 | |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Remote host closed the connection] | 10:08 | |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 10:08 | |
| n4nd0 | blackburn: I think you were faster answering :P | 10:32 |
| blackburn | faster than already? :) | 10:33 |
| blackburn | ah | 10:33 |
| blackburn | I see | 10:33 |
| blackburn | lol | 10:33 |
| n4nd0 | haha | 10:33 |
| blackburn | my answer is much more brief | 10:33 |
| n4nd0 | I am a literat | 10:34 |
| n4nd0 | :P | 10:35 |
| shogun-buildbot | build #481 of python_modular is complete: Failure [failed test_1] Build details are at http://www.shogun-toolbox.org/buildbot/builders/python_modular/builds/481 blamelist: sonne@debian.org, Phil.Tillet@gmail.com | 10:43 |
| blackburn | ehm | 10:46 |
| blackburn | wow outofmemoryerror on server with weblogic | 11:07 |
| n4nd0 | nice one | 11:08 |
| -!- av3ngr [av3ngr@nat/redhat/x-ujqsetgbcmptahsn] has quit [Quit: That's all folks!] | 11:10 | |
| blackburn | JVM version Java HotSpot(TM) Client VM 1.4.2_05-b04 OS Linux, ver: 2.6.18-194.el5 | 11:10 |
| blackburn | huh pretty old one | 11:10 |
| shogun-buildbot | build #476 of ruby_modular is complete: Failure [failed test_1] Build details are at http://www.shogun-toolbox.org/buildbot/builders/ruby_modular/builds/476 blamelist: sonne@debian.org, Phil.Tillet@gmail.com | 11:16 |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Ping timeout: 276 seconds] | 11:37 | |
| -!- wiking_ [~wiking@78-23-189-112.access.telenet.be] has joined #shogun | 11:52 | |
| -!- wiking_ [~wiking@78-23-189-112.access.telenet.be] has quit [Changing host] | 11:53 | |
| -!- wiking_ [~wiking@huwico/staff/wiking] has joined #shogun | 11:53 | |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Ping timeout: 240 seconds] | 11:56 | |
| -!- wiking_ is now known as wiking | 11:56 | |
| blackburn | 24gb and 12 cores o_o | 11:58 |
| blackburn | I wish I could use it to train some svms :D | 11:58 |
| -!- vikram360 [~vikram360@117.192.175.234] has quit [Ping timeout: 244 seconds] | 12:00 | |
| blackburn | uricamic: are you familiar with libocas? | 12:20 |
| uricamic | blackburn: yes | 12:23 |
| blackburn | uricamic: can it solve the following slightly modified problem: | 12:24 |
| blackburn | ||w||^2 + w0 w + ..? | 12:25 |
| blackburn | w0 is obtained before so can be considerd as constant vector | 12:25 |
| blackburn | I am lame with it :D | 12:27 |
| -!- PhilTillet [~Philippe@157.159.42.154] has joined #shogun | 12:40 | |
| uricamic | well I will look at it, but I am afraid that it cannot be used for that | 12:40 |
| uricamic | blackburn: the .. in your question means the rest of the original equation in OCAS solver? | 12:44 |
| blackburn | uricamic: yes sure | 12:44 |
| blackburn | uricamic: actually I'm interested in something similar to crammer-singer | 12:45 |
| blackburn | so even \sum_m ||w_m||^2 + \sum w_m w0_m + C \sum_i \xi_i | 12:45 |
| blackburn | s.t. <w_yi,x_i> - <w_m,x_i> <= 1 - \delta_{yi,m} - \xi_i | 12:46 |
| uricamic | blackburn: ok, in that case I think you cannot use libocas without modification, the additional w term will change the dual function | 12:46 |
| blackburn | I hope it is parseaable | 12:46 |
| blackburn | uricamic: hmm is libocas a dual solver? | 12:46 |
| uricamic | I think it is | 12:48 |
| -!- vikram360 [~vikram360@117.192.186.232] has joined #shogun | 12:48 | |
| blackburn | uricamic: it looks for me like it is a primal solver | 12:52 |
| -!- vikram360 [~vikram360@117.192.186.232] has quit [Ping timeout: 260 seconds] | 12:53 | |
| -!- vikram360 [~vikram360@117.192.160.167] has joined #shogun | 12:54 | |
| uricamic | blackburn: sorry my mistake, it is | 12:54 |
| blackburn | why I am asking is I am curious how hard it would be to modify it | 12:55 |
| uricamic | blackburn: I am looking on the libocas.cpp code now, and it looks that e.g. in svm_ocas_solver it uses dual function | 13:08 |
| uricamic | it calls libqp_splx_solver and computes the wights of alpha | 13:08 |
| blackburn | you are right | 13:09 |
| uricamic | *weights | 13:09 |
| blackburn | that's all confusing | 13:09 |
| uricamic | and the transformation to the primal objective function is done in compute_W, which uses this alpha | 13:11 |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Remote host closed the connection] | 13:36 | |
| -!- wiking [~wiking@vpnd095.ugent.be] has joined #shogun | 13:37 | |
| -!- wiking [~wiking@vpnd095.ugent.be] has quit [Changing host] | 13:37 | |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 13:37 | |
| -!- harshit_ [~harshit@182.68.246.67] has joined #shogun | 14:39 | |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 14:42 | |
| -!- harshit_ [~harshit@182.68.246.67] has quit [Ping timeout: 245 seconds] | 14:51 | |
| blackburn | totally DEADLY today | 14:58 |
| blackburn | n4nd0: what's up? | 14:58 |
| n4nd0 | blackburn: bah, not much, boring day so far | 14:59 |
| n4nd0 | blackburn: what about you? | 14:59 |
| blackburn | n4nd0: totally BORING | 14:59 |
| blackburn | I guess it is the time to rename shogun | 14:59 |
| n4nd0 | really? to what? | 15:00 |
| blackburn | n4nd0: I preferred CCCP | 15:00 |
| n4nd0 | that stands for? | 15:00 |
| blackburn | n4nd0: USSR | 15:00 |
| blackburn | back in back in | 15:01 |
| blackburn | back in USSR | 15:01 |
| blackburn | ;) | 15:01 |
| n4nd0 | back to black maybe :P | 15:01 |
| blackburn | n4nd0: it seems you are not the biggest fan of beatles :) | 15:02 |
| n4nd0 | blackburn: probably not, but I like them quite much :) | 15:03 |
| n4nd0 | blackburn: why so? | 15:03 |
| blackburn | n4nd0: they had this song :) | 15:04 |
| * n4nd0 is listening Back in the USSR | 15:05 | |
| n4nd0 | I didn't know about it :) | 15:05 |
| -!- vikram360 [~vikram360@117.192.160.167] has quit [Ping timeout: 276 seconds] | 15:08 | |
| -!- PhilTillet [~Philippe@157.159.42.154] has quit [Ping timeout: 248 seconds] | 15:24 | |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has left #shogun [] | 15:28 | |
| -!- emrecelikten [~Anubis@213.74.228.187] has joined #shogun | 15:47 | |
| emrecelikten | Hello all | 15:47 |
| blackburn | uricamic: is there any speedup with GS? | 15:52 |
| uricamic | blackburn: it depends on the size of kernel matrix, I think | 15:53 |
| blackburn | uricamic: sure with large kernel matrix pinv wouldn't work at all :) | 15:54 |
| uricamic | I have also tried variant which will not compute the whole kernel matrix, but it was very slow | 15:54 |
| blackburn | really? | 15:54 |
| uricamic | well, maybe I haven't done that in the most clever way | 15:55 |
| blackburn | ah you need each element there | 15:55 |
| uricamic | I took the row of matrix in each step, but I think that this allocation and freeing of memory is killing the performance | 15:56 |
| blackburn | uricamic: how many iterations it requires? | 15:56 |
| wiking | uricamic: hey i was wondering if you'll have some times this week to have a chat about the integration of libqp into shogun | 15:56 |
| uricamic | depends on the epsilon and also on the initialization | 15:57 |
| uricamic | wiking: libqp? | 15:57 |
| uricamic | wiking: I thought it is already there | 15:57 |
| wiking | well it's a very immature integration | 15:57 |
| uricamic | blackburn: I will try to think about this GS for KRR, maybe it can be simplified which could bring some performance increase | 15:58 |
| uricamic | wiking: ok | 15:58 |
| wiking | and afaik you'll use it in your bmrm , or? | 15:58 |
| uricamic | wiking: yep, I am using it there | 15:58 |
| wiking | yeah and i'm planning to use it in my latent svm implementation | 15:59 |
| wiking | thus maybe if you have some time we could have a little chat about the libqp integration into shogun | 15:59 |
| uricamic | wiking: sure, I will be on IRC all this week, I think | 16:00 |
| wiking | cool | 16:00 |
| wiking | maybe then tomorrow | 16:00 |
| wiking | today is not the best for me | 16:00 |
| uricamic | sure, neither for me, I am leaving soon | 16:00 |
| uricamic | so tommorow in the morning or afternoon? | 16:00 |
| blackburn | that day is totally boriinggggg | 16:01 |
| wiking | uricamic: morning means for you? | 16:01 |
| wiking | i mean for me tomorrow before noon around 10am would be fine | 16:01 |
| uricamic | after 9am | 16:01 |
| uricamic | ok | 16:02 |
| wiking | ok cool, so how about 10am? | 16:02 |
| wiking | cool | 16:02 |
| wiking | i'll be around | 16:02 |
| wiking | thnx a lot! | 16:02 |
| uricamic | I hope we have the same timezone :D | 16:02 |
| wiking | yep | 16:02 |
| wiking | you are from .cz right? | 16:02 |
| uricamic | yep | 16:02 |
| uricamic | ok, fine :) | 16:02 |
| wiking | diky | 16:02 |
| uricamic | neni zac :D | 16:02 |
| wiking | yeah about this is my level of czech ... i think i could order some beers as well ;P | 16:03 |
| wiking | dva piva? ;0 | 16:03 |
| blackburn | wiking: https://github.com/shogun-toolbox/shogun/pull/450 what would you say about my last comment? | 16:03 |
| uricamic | *dve | 16:03 |
| blackburn | sound like russian | 16:03 |
| wiking | ah ok | 16:03 |
| wiking | it's different then a bit | 16:03 |
| blackburn | dva piva is totally correct russian | 16:03 |
| wiking | hahah yeah i think serbian is closer to russian | 16:04 |
| wiking | ;) | 16:04 |
| uricamic | all of these are quite similar | 16:04 |
| blackburn | however dve butylki vodki would make it more russian | 16:04 |
| wiking | blackburn: i'll check the comment just a sec | 16:04 |
| wiking | uricamic: yeps | 16:04 |
| blackburn | uricamic: are you able to understand russian then? ;) | 16:04 |
| wiking | uricamic: this is how i survive when i'm in .cz ;) | 16:04 |
| uricamic | whenever I hear some russian counting I feel like hearing czech :) | 16:04 |
| uricamic | blackburn: only a little | 16:04 |
| blackburn | my friend studying in cz teached me how to count in czech | 16:05 |
| blackburn | however I do not remember that :( | 16:05 |
| uricamic | for example some words are completely the same, but some have exactly the opposite meaning :) | 16:05 |
| blackburn | uricamic: how does it sound like? | 16:05 |
| wiking | for sure they understand: jedan, dva, tri, cetri, pet.... | 16:05 |
| wiking | ;) | 16:05 |
| wiking | maybe there's an -i on the end ;P | 16:05 |
| uricamic | jeden, dva, tri, ctyri, pet | 16:05 |
| wiking | see it's very similar :) | 16:06 |
| blackburn | odin dva try chetyre pyat schest sem' vosem' devyat' | 16:06 |
| wiking | blackburn: your problem is with how to find out the size of an array? | 16:06 |
| blackburn | wiking: it is not a problem of mine ;) | 16:06 |
| uricamic | counting for sure, but for example word "voni" has the exactly opposite meaning in russian than in czech :) | 16:06 |
| blackburn | wiking: do you agree it *can't* work at all? | 16:06 |
| wiking | i mean this should be fine: sizeof(vec)/sizeof(variable that the array is made of) | 16:06 |
| blackburn | uricamic: voni? some smells? | 16:06 |
| wiking | that's totally legal in ansi c | 16:07 |
| uricamic | in czech it means that something smells nice, and in russian it means that somethins smells badly | 16:07 |
| blackburn | uricamic: yeap | 16:07 |
| wiking | of course you'll start having troubles | 16:07 |
| blackburn | wiking: I am afraid it would not work still | 16:07 |
| wiking | it will | 16:07 |
| wiking | except if it's a pointer | 16:07 |
| wiking | ;) | 16:07 |
| blackburn | it is | 16:08 |
| blackburn | http://pastebin.com/VYvPnkiP | 16:08 |
| blackburn | it would work only for static allocated arrays afaik | 16:08 |
| wiking | yeah as said pointers will make you feel bad ;) | 16:08 |
| wiking | since you'll get back the pointer size | 16:08 |
| blackburn | so zero length alway | 16:08 |
| blackburn | s | 16:08 |
| wiking | no pointer size = 4 or 8 | 16:08 |
| wiking | depends on the arch | 16:08 |
| blackburn | ah nevertheless it is not correct | 16:09 |
| wiking | yes with pointer you'll have troubles | 16:09 |
| wiking | and this syntax is anyways bogus | 16:09 |
| wiking | (sizeof array)/sizeof(int); | 16:09 |
| wiking | it should be like sizeof(array)/sizeof(int) | 16:09 |
| wiking | if | 16:10 |
| wiking | ;) | 16:10 |
| wiking | blackburn: you can check your fav help as well, i.e. stack overflow; quote: "It is worth noting that sizeof doesn't help if you are dealing with a pointer to an array:" | 16:10 |
| -!- harshit_ [~harshit@182.68.246.67] has joined #shogun | 16:11 | |
| wiking | and of course the other problem here is what if you change your function arg in the future | 16:11 |
| blackburn | wiking: hah why stack overflow is my fav help? | 16:11 |
| wiking | blackburn: just joking ;) | 16:11 |
| wiking | anyhow if in future you make a function arg type change you are (not you but any 3rd person) most likely going to forget to change the type in /sizeof(.) | 16:12 |
| wiking | so you'll end up with a bad vector size obviously | 16:12 |
| wiking | so it's far from being safe | 16:12 |
| blackburn | wiking: I was really surprised to see that here | 16:12 |
| wiking | much better to pass the vector size via the function arg, as anywhere else in shogun ;P | 16:12 |
| blackburn | I mean this way of obtaining a size of array | 16:13 |
| wiking | blackburn: yeah this is a dirty hack from ansi c ;) | 16:13 |
| harshit_ | blackburn: how can I make my current fork exactly same as upstream, I don't want to rebase I want to get to the current state of upstream master | 16:13 |
| wiking | blackburn: it works until you work on the stack... as soon as you start using the heap you'll have problems | 16:13 |
| blackburn | wiking: in my example it is on stack but doesn't work | 16:13 |
| blackburn | harshit_: why don't you want to rebase? | 16:14 |
| -!- ishaanmlhtr [~chatzilla@101.63.121.9] has joined #shogun | 16:14 | |
| harshit_ | I have made some changes in my fork that I want to delete .. | 16:14 |
| wiking | blackburn: true that :) | 16:14 |
| blackburn | harshit_: did you commit it then? | 16:14 |
| harshit_ | yeah :( | 16:15 |
| harshit_ | so do I need to delete my current fork | 16:15 |
| harshit_ | and fork again ? | 16:15 |
| blackburn | no you can reset your state and push with --force | 16:15 |
| harshit_ | reset ?? how to do that ? | 16:16 |
| blackburn | harshit_: something like git reset --hard upstream/HEAD | 16:16 |
| blackburn | wiking: am I right? | 16:16 |
| wiking | blackburn: yeah | 16:16 |
| wiking | harshit_: have you commit? | 16:16 |
| blackburn | he did | 16:17 |
| wiking | i mean your code | 16:17 |
| wiking | into your own branch | 16:17 |
| harshit_ | wiking: yeah I have commit some changes | 16:17 |
| wiking | aaaah | 16:17 |
| wiking | well then it's a bit tricky | 16:17 |
| blackburn | wiking: I can't see any other way but hard reset and force push | 16:17 |
| wiking | since you'll repo is going to be a bit fucked up with you do a rebase | 16:17 |
| wiking | wh | 16:17 |
| wiking | blackburn: you can remove commites | 16:17 |
| wiking | *commits | 16:17 |
| blackburn | wiking: how? | 16:18 |
| wiking | just you need to do a rebase | 16:18 |
| wiking | which is usually a pain in the ass | 16:18 |
| wiking | if somebody is following your repo | 16:18 |
| harshit_ | why not delete and fork again ? | 16:18 |
| blackburn | harshit_: yes it is the simplest way | 16:18 |
| wiking | it's simple :) | 16:18 |
| harshit_ | :) | 16:18 |
| wiking | blackburn: yours would do that | 16:19 |
| wiking | git reset --hard upstream/HEAD | 16:19 |
| wiking | that'd remove the commits | 16:19 |
| blackburn | not really remove but jump to another state | 16:19 |
| wiking | and what happens with the prev commits? :) | 16:19 |
| wiking | i mean that are after HEAD? | 16:20 |
| blackburn | wiking: hmm are they really deleted from index? | 16:21 |
| wiking | yep | 16:22 |
| wiking | you'll never get those commits back | 16:22 |
| wiking | unless you've saved them somewhere... other branch or somethin | 16:22 |
| blackburn | but can't you access it by sha1? | 16:22 |
| wiking | not in that branch no | 16:23 |
| blackburn | wiking: it seems we spend days solving puzzles | 16:23 |
| wiking | :D | 16:24 |
| -!- vikram360 [~vikram360@117.192.160.167] has joined #shogun | 16:27 | |
| -!- ishaanmlhtr [~chatzilla@101.63.121.9] has quit [Quit: ChatZilla 0.9.88.2 [Firefox 9.0.1/20111220165912]] | 16:33 | |
| -!- emrecelikten [~Anubis@213.74.228.187] has quit [Ping timeout: 245 seconds] | 16:49 | |
| @sonney2k | uricamic, around? | 17:03 |
| @sonney2k | uricamic, how many iterations does GS need to get eps precision? | 17:04 |
| -!- harshit_ [~harshit@182.68.246.67] has quit [Ping timeout: 264 seconds] | 17:07 | |
| blackburn | sonney2k: I am afraid he is afk | 17:08 |
| blackburn | (as he told he is leaving) | 17:09 |
| uricamic | sonney2k: I am still here | 17:09 |
| blackburn | :D | 17:09 |
| blackburn | that's nice then | 17:09 |
| uricamic | I am now working on your comments | 17:10 |
| uricamic | but I will have to leave soon | 17:10 |
| @sonney2k | blackburn, yeah I guess so too... I've studied his code and I guess it needs some kernel caching routines to be fast w/ GS | 17:10 |
| blackburn | sonney2k: here already | 17:10 |
| @sonney2k | blackburn, unfortunately we don't have that in CKernel ... we only have crappy svmlight kernel cache business there | 17:10 |
| blackburn | sonney2k: I mean uricamic is here | 17:11 |
| blackburn | :) | 17:11 |
| @sonney2k | so we in fact need one general solution that one can use with distances etc too | 17:11 |
| blackburn | but yes I agree we need nice caching | 17:11 |
| @sonney2k | uricamic, hey | 17:11 |
| uricamic | sonney2k: I am working on the comments | 17:12 |
| uricamic | sonney2k: then I will do the benchmarks | 17:12 |
| blackburn | sonney2k: someone could do that while gsocing may be ;) | 17:12 |
| @sonney2k | uricamic, so any idea how many GS iterations you need? | 17:15 |
| uricamic | sonney2k: I haven't measure it in this implementation, but when I was trying my first implementation in MATLAB it was around 700 for eps=1e-5 | 17:16 |
| @sonney2k | uricamic, that is all I wanted to know - ok then you will need some kind of cache and clever strategy / way to iterate over examples for this to be any fast then | 17:19 |
| uricamic | sonney2k: yes | 17:20 |
| uricamic | I really have to go now, see you | 17:23 |
| -!- uricamic [9320543b@gateway/web/freenode/ip.147.32.84.59] has quit [Quit: Page closed] | 17:23 | |
| -!- blackburn [5bdfb203@gateway/web/freenode/ip.91.223.178.3] has quit [Quit: Page closed] | 17:32 | |
| -!- emrecelikten [~Anubis@176.33.63.94] has joined #shogun | 17:32 | |
| -!- blackburn [~qdrgsm@188.168.2.179] has joined #shogun | 18:23 | |
| -!- akshayms [75c0dcbc@gateway/web/freenode/ip.117.192.220.188] has joined #shogun | 18:41 | |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has joined #shogun | 18:52 | |
| @sonney2k | n4nd0, hey! good evening! | 18:52 |
| n4nd0 | sonney2k: hey there! | 18:53 |
| n4nd0 | good evening guys | 18:53 |
| * sonney2k pastes in all the timezones into the timeanddate meeting planner | 18:53 | |
| n4nd0 | meeting planner, sounds cool | 18:54 |
| -!- harshit_ [~harshit@182.68.246.67] has joined #shogun | 18:55 | |
| @sonney2k | n4nd0, yeah dammed we have 6 timezones or so | 19:04 |
| n4nd0 | oh | 19:04 |
| n4nd0 | I can adapt my timezone if necessary :P | 19:05 |
| @sonney2k | we are basically dead already because we have one mentor in NY | 19:07 |
| @sonney2k | and one in melbourne | 19:07 |
| @sonney2k | and some spread inbetween | 19:07 |
| @sonney2k | so it is like either the NY guys suffer or the ozzies | 19:08 |
| n4nd0 | sonney2k: who is the mentor in NY? | 19:09 |
| @sonney2k | christian widmer | 19:10 |
| n4nd0 | ok | 19:10 |
| @sonney2k | UTC 11 hrs or 12hrs seems to be the only viable time | 19:11 |
| @sonney2k | well in one week the officially accepted students will be announced | 19:16 |
| @sonney2k | so we should have some kickoff meeting that informs about how things work and they way we want them to work :) | 19:17 |
| n4nd0 | :) | 19:17 |
| n4nd0 | sonney2k: by the way, one doubt about JL's cover tree | 19:17 |
| n4nd0 | sonney2k: so when m_q != 1, since the cover tree doesn't output the neighbors ordered by distance | 19:18 |
| n4nd0 | it would be required to compute the distance to the k neighbors and sort them | 19:19 |
| n4nd0 | something similar to what is done in the method to classify for different k | 19:20 |
| n4nd0 | when you said on github | 19:21 |
| n4nd0 | "I would just speed up the most common q=1 case with the covertree." | 19:21 |
| n4nd0 | do you mean that this computation of the distances and sorting shouldn't be done right? | 19:21 |
| n4nd0 | i.e. no cover tree + m_q != 1 | 19:21 |
| @sonney2k | n4nd0, I am not sure what you are saying | 19:23 |
| @sonney2k | I meant m_q !=1 -> no cover tree | 19:23 |
| n4nd0 | haha ok | 19:23 |
| @sonney2k | slow | 19:23 |
| n4nd0 | ok | 19:23 |
| @sonney2k | but if you want to do the sorting - feel free :) | 19:23 |
| -!- wiking_ [~wiking@huwico/staff/wiking] has joined #shogun | 19:24 | |
| n4nd0 | it is ok like you say | 19:24 |
| @sonney2k | it would be the same thing because you dont' have to sort :) | 19:24 |
| n4nd0 | you just condensed all the stuff I said in a couple of sentences :D | 19:24 |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Ping timeout: 248 seconds] | 19:27 | |
| -!- wiking_ [~wiking@huwico/staff/wiking] has quit [Ping timeout: 240 seconds] | 19:28 | |
| -!- harshit_ [~harshit@182.68.246.67] has quit [Read error: Connection timed out] | 19:50 | |
| -!- harshit_ [~harshit@182.68.246.67] has joined #shogun | 19:51 | |
| blackburn | sonney2k: being chris in NY doesn't lead to any inconveniences I think ;) | 19:51 |
| blackburn | he tends to appear randomly anyway | 19:53 |
| blackburn | sonney2k: n4nd0: I can't agree m_q != 1 should be w/o covertree.. | 19:54 |
| -!- akshayms [75c0dcbc@gateway/web/freenode/ip.117.192.220.188] has quit [Quit: Page closed] | 19:55 | |
| -!- wiking [~wiking@we02c096.ugent.be] has joined #shogun | 19:57 | |
| -!- wiking [~wiking@we02c096.ugent.be] has quit [Changing host] | 19:58 | |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 19:58 | |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Client Quit] | 20:02 | |
| @sonney2k | blackburn, it will still be a problem to have a meeting with everyone | 20:02 |
| blackburn | sonney2k: did you know we want to send you a present - book on STL? ;) | 20:03 |
| -!- gsomix [~gsomix@83.234.54.52] has joined #shogun | 20:03 | |
| gsomix | hi | 20:03 |
| blackburn | prishel | 20:03 |
| blackburn | sonney2k: encourage gsomix with my favourite russian sentence of you | 20:04 |
| @sonney2k | prishel? | 20:04 |
| blackburn | sonney2k: 'came' | 20:04 |
| blackburn | sonney2k: but my fav is about work | 20:05 |
| gsomix | blackburn, idi rabotay? | 20:05 |
| @sonney2k | blackburn, very good - I realize that you can easily take over the project when I leave :D | 20:06 |
| blackburn | sonney2k: because of? | 20:06 |
| blackburn | :) | 20:06 |
| blackburn | sonney2k: I am still waiting you to get gsomix to work! | 20:07 |
| blackburn | :( | 20:09 |
| @sonney2k | so gsomix work ! | 20:12 |
| blackburn | sonney2k: "rabotatsch"! | 20:12 |
| blackburn | eh what a sadness :) | 20:12 |
| gsomix | you are funny, guys :) | 20:13 |
| gsomix | blackburn, add expression | 20:14 |
| blackburn | gsomix: which one you would like? | 20:14 |
| gsomix | "rabotatsch, bldjad'!" | 20:14 |
| blackburn | oh I didn't think about obscene stuff yet | 20:15 |
| gsomix | huh | 20:15 |
| gsomix | blackburn, but you are right - it's time to work. | 20:19 |
| blackburn | you got my implicit message right ;) | 20:19 |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 20:36 | |
| -!- nickon [~noneedtok@kotnet-147.kulnet.kuleuven.be] has joined #shogun | 20:41 | |
| blackburn | gsomix: what is you are working on? | 20:47 |
| gsomix | blackburn, SGVector, khm | 20:48 |
| blackburn | ah right | 20:48 |
| @sonney2k | blackburn, you wanted him to start working on caches right :D | 20:48 |
| blackburn | sonney2k: no that's damn hard I think | 20:49 |
| blackburn | I just have holes in my head and my thoughts slip away through it | 20:49 |
| gsomix | blackburn, tomorrow I learn about researches that are conducted at our university. | 20:53 |
| blackburn | ah how to drink 2 litres of vodka? | 20:54 |
| blackburn | what is the role of optics when you are drunk? | 20:54 |
| blackburn | how to burn up cucumber with laser to have vodka more comfortably? | 20:54 |
| @sonney2k | blackburn, vision correcting glasses for drunks! | 20:54 |
| blackburn | sonney2k: I imagine its surface | 20:55 |
| blackburn | kind of perlin noise lol | 20:55 |
| @sonney2k | blackburn, tell him about the animal tests they are conducting! | 20:55 |
| blackburn | sonney2k: you mean 2nd semester of optics for me? | 20:55 |
| -!- PhilTillet [~Philippe@157.159.42.154] has joined #shogun | 20:56 | |
| blackburn | sounds like cruel animal test | 20:56 |
| @sonney2k | yeah animals == students! | 20:56 |
| gsomix | blackburn, is it a future topic of my bachelor diploma? T___T | 20:56 |
| @sonney2k | that's the devastating truth | 20:56 |
| blackburn | gsomix: yeah some vodka stuff | 20:56 |
| blackburn | sonney2k: do you know they reject any work which title has no 'vodka' word? | 20:57 |
| @sonney2k | I knew it! | 20:57 |
| gsomix | it's time to become a physicist. no optics! T____T | 20:57 |
| @sonney2k | someone named vodking told me! | 20:57 |
| n4nd0 | :D | 20:58 |
| blackburn | sonney2k: my bachelor's work is title | 20:58 |
| blackburn | support vodka machine recognition | 20:58 |
| blackburn | titled* | 20:58 |
| blackburn | SVM | 20:58 |
| blackburn | I wish it was vector but they forced me to call it support vodka machine | 20:59 |
| @sonney2k | vodka really is the key to everything... | 21:00 |
| @sonney2k | without vodka R.I.P. | 21:00 |
| @sonney2k | no fun, no gsoc, no shogun, no theorems, no kernels, no support vodka machines! | 21:00 |
| blackburn | you catch things | 21:01 |
| @sonney2k | yeah I am fast in this | 21:01 |
| @sonney2k | that's because we had a brewing seminar for x-mas party at tomtom | 21:01 |
| @sonney2k | and you know once your blood got replaced by vodka there is nothing to worry about! | 21:02 |
| blackburn | sonney2k: heh | 21:02 |
| gsomix | blackburn, should I offer vodka to my future supervisor? | 21:03 |
| blackburn | gsomix: to sobolev? | 21:03 |
| gsomix | yep | 21:03 |
| blackburn | he seems to not be a big fan of it | 21:03 |
| gsomix | :( | 21:04 |
| blackburn | gsomix: consider kolomiets for that | 21:05 |
| n4nd0 | does that work in Russia, to buy things for the teachers? | 21:05 |
| gsomix | blackburn, ohoho. | 21:05 |
| n4nd0 | some friends tried it once in my school (for real!) but it didn't work | 21:05 |
| blackburn | n4nd0: to get exam passed? | 21:05 |
| n4nd0 | blackburn: yeah, for example | 21:05 |
| blackburn | yes pretty often unfortunately | 21:06 |
| blackburn | mostly money however | 21:06 |
| n4nd0 | the story in my university is quite fun actually | 21:06 |
| n4nd0 | they put a serrano on the hood of the car | 21:06 |
| blackburn | n4nd0: half of my group at univ bribed teacher to get physics passed | 21:07 |
| blackburn | 6000 roubles = 200$ each | 21:07 |
| n4nd0 | and went to the office with more stuff | 21:07 |
| gsomix | blackburn, congac (brandy) for Alimenkov | 21:07 |
| blackburn | ha | 21:07 |
| blackburn | n4nd0: did it work? | 21:08 |
| n4nd0 | blackburn: no | 21:08 |
| blackburn | n4nd0: as for your very first question | 21:08 |
| blackburn | it works to bribe anyone in russia | 21:09 |
| blackburn | it is just a matter of different cost ;) | 21:09 |
| n4nd0 | haha I see | 21:10 |
| n4nd0 | I actually shouldn't laugh, sad thing indeed | 21:10 |
| blackburn | n4nd0: police there tends to put a bottle in your ass if they don't like you :D | 21:11 |
| blackburn | I am not joking | 21:11 |
| blackburn | three cases recently one has died | 21:11 |
| gsomix | blackburn, brrr >__< this story... | 21:11 |
| n4nd0 | :O | 21:12 |
| n4nd0 | for real? hard to believe | 21:12 |
| n4nd0 | blackburn: I am not saying you're lying, that could be misunderstood :S | 21:12 |
| blackburn | n4nd0: yes in kazan' | 21:12 |
| blackburn | they put a bottle of champagne right to the ass | 21:12 |
| n4nd0 | not good | 21:13 |
| gsomix | blackburn, horror stories about Russia | 21:15 |
| blackburn | hah why not | 21:15 |
| -!- PhilTillet [~Philippe@157.159.42.154] has quit [Remote host closed the connection] | 21:17 | |
| gsomix | blackburn, I sleep badly, hehe | 21:18 |
| blackburn | n4nd0: remember you said to come up with some paper sounds like something good? | 21:31 |
| n4nd0 | blackburn: yes | 21:31 |
| emrecelikten | I think one of you guys recommended a good dataset website before, what was it? | 21:31 |
| n4nd0 | very good actually | 21:31 |
| blackburn | emrecelikten: mldata.org | 21:31 |
| emrecelikten | blackburn: Yep, that's it. Thanks | 21:31 |
| blackburn | n4nd0: I think it would be hard and time consuming to come up with strong journal article | 21:31 |
| n4nd0 | blackburn: why? | 21:32 |
| blackburn | however there is arxiv still | 21:32 |
| blackburn | and we could place some kind of paper there :) | 21:32 |
| n4nd0 | aham | 21:32 |
| n4nd0 | I didn't know about arxiv | 21:32 |
| blackburn | hmm it is openaccess and rather easy reviewed | 21:33 |
| blackburn | so you won't be rejected because this paper does no revolution in SO :) | 21:33 |
| n4nd0 | yeah sure, it could be a nice place to start with | 21:33 |
| blackburn | I would be happy to collaborate later on that | 21:33 |
| n4nd0 | blackburn: :) | 21:34 |
| n4nd0 | it looks that they not require the common format with two columns of text per page | 21:35 |
| n4nd0 | blackburn: by the way, did you or any of you blog about gsoc last year? | 21:36 |
| blackburn | no | 21:36 |
| blackburn | I actually do not think it is so useful though | 21:36 |
| n4nd0 | I think it is a good idea | 21:36 |
| blackburn | sonney2k: what do you think about adv ourselves and shogun using arXiv? :) | 21:39 |
| blackburn | and blogs | 21:39 |
| @sonney2k | well we have a meta-blog | 21:40 |
| blackburn | yours? | 21:40 |
| @sonney2k | http://shogun-toolbox.org/planet/ | 21:40 |
| @sonney2k | everyone that wants to be on it - send me the url | 21:41 |
| @sonney2k | and voila | 21:41 |
| blackburn | ah | 21:41 |
| blackburn | yes | 21:41 |
| @sonney2k | and please regularly write something | 21:41 |
| @sonney2k | I am damn lazy so I won't write more than once a year or so | 21:41 |
| @sonney2k | crazy .. .https://fgiesen.wordpress.com/ | 21:42 |
| * sonney2k gets tired | 21:42 | |
| blackburn | sonney2k: and what about arxiv stuff? | 21:42 |
| @sonney2k | blackburn, publish as much as you want :D | 21:45 |
| blackburn | sonney2k: hrr I am asking whether it is a good idea | 21:46 |
| @sonney2k | blackburn, depends what you want to achieve... | 21:50 |
| @sonney2k | if you want to become professor it is worth nothing | 21:51 |
| blackburn | sonney2k: me? professor? | 21:51 |
| @sonney2k | but to e.g. apply to something related to ML (also research) it can help | 21:51 |
| @sonney2k | blackburn, you drink vodka so you qualify | 21:52 |
| blackburn | don't you think I am too stupid^W programmer to be a professor? | 21:52 |
| @sonney2k | and you know the 'dawai dawai rabotatch' slogan pretty well | 21:52 |
| blackburn | finally you said that | 21:52 |
| @sonney2k | wellyou have to stop programming of course and let your slaves^H^H^Hstudents to this | 21:52 |
| blackburn | sonney2k: no seriously no chance | 21:54 |
| n4nd0 | sonney2k: but now, while we are studying, isn't it a good idea to do some programming job to become professor in the future? | 21:54 |
| blackburn | brb | 21:54 |
| n4nd0 | I meant job, like work or collaboration as we do here | 21:54 |
| -!- karlnapf [~heiko@host86-177-177-13.range86-177.btcentralplus.com] has joined #shogun | 21:58 | |
| -!- wiking [~wiking@huwico/staff/wiking] has quit [Remote host closed the connection] | 21:58 | |
| -!- wiking [~wiking@vpnb164.ugent.be] has joined #shogun | 21:58 | |
| -!- wiking [~wiking@vpnb164.ugent.be] has quit [Changing host] | 21:58 | |
| -!- wiking [~wiking@huwico/staff/wiking] has joined #shogun | 21:58 | |
| @sonney2k | n4nd0, all profs did real work at some point - they started out as researchers, group leaders, ... | 22:07 |
| @sonney2k | so yes it helps + you need to slowly become some kind of leader (like backburn :D | 22:07 |
| @sonney2k | hey karlnapf | 22:07 |
| karlnapf | sonney2k, hi there | 22:08 |
| n4nd0 | sonney2k: thank you :) | 22:08 |
| karlnapf | sonney2k, good to catch you, wanted to talk about subsets once more | 22:08 |
| karlnapf | I am currently working on moving all the stack stuff to a separate class | 22:09 |
| -!- harshit_ [~harshit@182.68.246.67] has quit [Remote host closed the connection] | 22:09 | |
| karlnapf | which does everything, instead of doing this by hand in every class | 22:09 |
| karlnapf | sonney2k, I think this should solve all subset stuff once and for all | 22:10 |
| karlnapf | I think it will also be possible to migrate the old plain Subsets into that new system | 22:11 |
| -!- PhilTillet [9d9f0a0e@gateway/web/freenode/ip.157.159.10.14] has joined #shogun | 22:20 | |
| PhilTillet | Hello | 22:20 |
| karlnapf | hi | 22:21 |
| @sonney2k | karlnapf, sounds great | 22:23 |
| @sonney2k | (as usual) | 22:23 |
| karlnapf | it will also be easier than its now | 22:23 |
| @sonney2k | I guess you should just do it then and I can only hope that you are only 150% overloaded :) | 22:23 |
| karlnapf | tell me about it :) | 22:24 |
| karlnapf | Well I cannot compete with you? | 22:24 |
| karlnapf | ehm not ? , ! | 22:24 |
| karlnapf | what about you and your family? are things getting more relaxed? | 22:25 |
| @sonney2k | I can sleep at night now! | 22:28 |
| @sonney2k | (since about the week before easter) | 22:28 |
| @sonney2k | and that is a big big big + | 22:28 |
| @sonney2k | which reminds me | 22:28 |
| @sonney2k | I should really sleep now | 22:28 |
| @sonney2k | karlnapf, nice talking to you if only briefly | 22:28 |
| @sonney2k | cu | 22:28 |
| karlnapf | sonney2k, ok enjoy :) | 22:29 |
| blackburn | karlnapf: hey there | 22:30 |
| karlnapf | blackburn, hi, how is russia? ;) | 22:31 |
| -!- nickon [~noneedtok@kotnet-147.kulnet.kuleuven.be] has quit [Quit: ( www.nnscript.com :: NoNameScript 4.22 :: www.esnation.com )] | 22:32 | |
| blackburn | karlnapf: stays the same I guess | 22:32 |
| blackburn | karlnapf: btw I had some crazy thought | 22:32 |
| karlnapf | blackburn, tell me | 22:33 |
| blackburn | what if I write some things to you in german and you will check/correct it? :D | 22:33 |
| karlnapf | you wanna learn German? | 22:33 |
| blackburn | yes | 22:33 |
| blackburn | I know you are busy so 'no' would be ok too ;) | 22:34 |
| karlnapf | nice, I like that. | 22:34 |
| karlnapf | Well what about in June? | 22:34 |
| blackburn | yes sure | 22:35 |
| karlnapf | after my exams? | 22:35 |
| blackburn | deal | 22:35 |
| karlnapf | Then I am happy to help you | 22:35 |
| karlnapf | I encourage everybody in learning German :) | 22:35 |
| karlnapf | why you want to do that? | 22:35 |
| blackburn | karlnapf: I could help you with russian if you want | 22:35 |
| blackburn | karlnapf: I want to visit deutschland and probably stay there | 22:35 |
| karlnapf | Would be an idea, but thats probably not before winter, to much stuff to do before | 22:36 |
| karlnapf | really? | 22:36 |
| karlnapf | any concrete plans? | 22:36 |
| blackburn | and damn you are all germans | 22:36 |
| blackburn | no but may be chris would call me to be his phd, who knows? ;) | 22:36 |
| karlnapf | oh cool :) | 22:37 |
| karlnapf | maybe we will meet then | 22:37 |
| karlnapf | I am applying to the MPI | 22:37 |
| blackburn | heh who knows again | 22:38 |
| blackburn | it would be useful anyway | 22:38 |
| blackburn | karlnapf: to talk is the only way I guess | 22:38 |
| karlnapf | yes indeed. | 22:39 |
| blackburn | less or more you now understand my english and should work for german | 22:39 |
| karlnapf | yeah you will get that | 22:39 |
| karlnapf | and you had it in school so should be easy | 22:40 |
| blackburn | it was pretty bad in school | 22:40 |
| karlnapf | mmh, but now you have me correcting you :( | 22:40 |
| karlnapf | :8 | 22:40 |
| blackburn | heh | 22:40 |
| blackburn | I have known more from rammstein songs than from school | 22:41 |
| karlnapf | hehe | 22:41 |
| karlnapf | rammstein | 22:41 |
| karlnapf | crazy guys | 22:41 |
| karlnapf | once saw them live | 22:41 |
| karlnapf | fire all over the place | 22:41 |
| blackburn | it is easy to distinguish their german words for me | 22:41 |
| karlnapf | but nobody talks like them here ;) | 22:42 |
| blackburn | yes I hope so | 22:42 |
| blackburn | and actually their songs are about some crazy shit | 22:42 |
| blackburn | I was pretty surprised translated zwitter | 22:43 |
| blackburn | karlnapf: eins, zwei, drei, fier, f?nf, sechs, sieben, acht, neun, zehn, zw?lf! | 22:44 |
| blackburn | I know that | 22:44 |
| karlnapf | vier | 22:44 |
| blackburn | ohh | 22:44 |
| karlnapf | and zehn elf zw?lf :) | 22:44 |
| blackburn | hahahah | 22:44 |
| blackburn | 95% | 22:44 |
| blackburn | karlnapf: v as f is a bit confusing | 22:45 |
| blackburn | v?gel | 22:45 |
| karlnapf | yeah many people confuse these | 22:45 |
| karlnapf | btw it owuldnt be too bad if you would start learning it here | 22:45 |
| karlnapf | I think many people in t?bingen talk english all day | 22:46 |
| karlnapf | Arthur Gretton was there a few years and cannot speak German | 22:46 |
| blackburn | karlnapf: ah yes but I am rather curious than planning something | 22:46 |
| blackburn | it is always useful to speak diff langs | 22:46 |
| karlnapf | yea true | 22:47 |
| karlnapf | very nice for traveling | 22:47 |
| karlnapf | I want to get into more languages some time | 22:47 |
| n4nd0 | good night guys | 22:48 |
| blackburn | n4nd0: see you! | 22:49 |
| -!- n4nd0 [~nando@s83-179-44-135.cust.tele2.se] has quit [Quit: leaving] | 22:49 | |
| blackburn | karlnapf: are you applying for Phd at MPI? | 22:49 |
| karlnapf | n4nd0, good night | 22:49 |
| karlnapf | blackburn, yes I think I will do that in a few month | 22:49 |
| karlnapf | (among other places) | 22:50 |
| blackburn | karlnapf: but what about gretton? | 22:50 |
| karlnapf | also an idea | 22:50 |
| blackburn | I thought you are going to work with him | 22:50 |
| karlnapf | but I can only apply in Dec 2012 | 22:50 |
| karlnapf | for Sept 2013 | 22:50 |
| karlnapf | pretty late | 22:50 |
| karlnapf | but perhaps there is a way of bridging this gap | 22:50 |
| karlnapf | dont really know yet | 22:51 |
| karlnapf | I wrote to some people | 22:52 |
| karlnapf | but I want to concentrate on my work currently, thats more important | 22:52 |
| blackburn | karlnapf: I see | 22:53 |
| gsomix | good night, guys | 22:54 |
| blackburn | another one bites the dust | 22:54 |
| karlnapf | gsomix, gn8 | 22:54 |
| karlnapf | hehe ;) | 22:54 |
| blackburn | gsomix: spokoynoy drochi! | 22:54 |
| gsomix | blackburn, :3 | 22:54 |
| blackburn | uh that's kind of hard to understand joke | 22:55 |
| blackburn | karlnapf: so you want to do bioinf? | 22:57 |
| blackburn | everybody does this thing :D | 22:57 |
| karlnapf | blackburn, mmmh I was a bit more sure about this a year ago | 22:58 |
| blackburn | but actually only in shogun neighborhood probably | 22:58 |
| karlnapf | currently I am more interested in kernel stuff and bayesian stuff | 22:58 |
| karlnapf | but who knows | 22:58 |
| karlnapf | this MMD thing might be a nice direction | 22:58 |
| blackburn | whoa I always hated that bayesian stuff | 22:58 |
| blackburn | networks, etc | 22:58 |
| karlnapf | optimization, kernels, statistics | 22:58 |
| karlnapf | I kind of like the gaussian processes | 22:58 |
| blackburn | probably this is because I do not understand it well | 22:59 |
| karlnapf | which is just bayesian linear regression in the feeature space | 22:59 |
| blackburn | karlnapf: yeah it seems a lot of people like GPs | 22:59 |
| blackburn | chris does afaik | 22:59 |
| karlnapf | no surprise, they are quite recent | 23:00 |
| karlnapf | and really cool | 23:00 |
| karlnapf | not cool for large scale stuff | 23:00 |
| karlnapf | at least out of the box | 23:00 |
| karlnapf | I havent tried them with some kernel matrix approximation | 23:00 |
| blackburn | karlnapf: is it only for regression? are classification results so well too? | 23:01 |
| karlnapf | yes | 23:01 |
| karlnapf | check out this book by carl rasmussen | 23:01 |
| karlnapf | awesome | 23:01 |
| karlnapf | currently studying this stuff for exams | 23:01 |
| blackburn | I've glanced over it before | 23:02 |
| karlnapf | I fell there is so much stuff | 23:04 |
| karlnapf | have no idea how to decide on anything | 23:04 |
| karlnapf | but probably thats handled by the people one konws | 23:04 |
| karlnapf | knows | 23:04 |
| blackburn | karlnapf: I just realized that I will suggest to study GPs to my gf | 23:06 |
| karlnapf | what??? | 23:07 |
| blackburn | she was excited about random processes studies | 23:07 |
| karlnapf | lol, she likes that? | 23:07 |
| blackburn | yes but not very familiar with ML still | 23:07 |
| blackburn | her bachelor's work is about multiclass svms | 23:07 |
| karlnapf | hehe, funny, you are a ML couple | 23:08 |
| blackburn | but she doesn't like it so much | 23:08 |
| blackburn | I have to mentor this while professors here are lame idiots | 23:08 |
| karlnapf | lol | 23:09 |
| wiking | yeeey i have a competitor ! | 23:10 |
| karlnapf | you cannot escape the ML then | 23:10 |
| blackburn | karlnapf: why? | 23:10 |
| blackburn | wiking: which? | 23:10 |
| karlnapf | blackburn, just joking | 23:10 |
| wiking | blackburn: saw the mails on shogun mailing list for latent svm | 23:10 |
| karlnapf | wiking, whats happening=? | 23:10 |
| blackburn | karlnapf: but I didn't get the joke :D | 23:11 |
| karlnapf | well you work all day on ML stuff and then you return home and continue working on ML stuff, and then youre talking about ML stuff in bed :D | 23:11 |
| blackburn | hahah | 23:12 |
| blackburn | karlnapf: I wish I was working on ML | 23:12 |
| karlnapf | what are you currently doing? | 23:12 |
| blackburn | karlnapf: working at netcracker and studying some crazy shit | 23:13 |
| blackburn | but I am going to finish with both activities | 23:13 |
| blackburn | i.e. leave job for summer and pass exams :D | 23:13 |
| karlnapf | nice | 23:14 |
| blackburn | karlnapf: I am pretty tired with development in such huge company | 23:14 |
| karlnapf | why? | 23:15 |
| blackburn | for example oneliner fix took a week recently | 23:15 |
| blackburn | just because of being "enterprise"/size/etc | 23:15 |
| karlnapf | oh that sucks | 23:15 |
| blackburn | karlnapf: another example is just what I do | 23:17 |
| karlnapf | I am currently a bit annoyed by studying for exams .... so much stuff | 23:17 |
| blackburn | e.g. today I fixed backpropagation of component associations related to component instances with vertical links while decomposing two service orders | 23:18 |
| karlnapf | ich verstehe nur Bahnhof | 23:18 |
| blackburn | you understand ... | 23:19 |
| karlnapf | "I understand just train-station" means: I dont understand anything ;) | 23:19 |
| blackburn | hah | 23:19 |
| blackburn | karlnapf: that is the problem | 23:19 |
| blackburn | I used to learn stuff that makes no sense in outer world | 23:19 |
| karlnapf | how do you mean that? | 23:20 |
| blackburn | I've learnt nothing but some netcracker-specific stuff | 23:20 |
| karlnapf | oh | 23:20 |
| karlnapf | mmh | 23:20 |
| karlnapf | but you always train your mind when you do this | 23:21 |
| blackburn | I wouldn't say so | 23:21 |
| karlnapf | jipiie my shogun compiles again | 23:21 |
| blackburn | you are right it is not harmful | 23:21 |
| blackburn | but not very useful | 23:21 |
| karlnapf | well its soon over :) | 23:21 |
| karlnapf | blackburn, I have to leave now | 23:22 |
| blackburn | yeah I prefer to full-time in gsoc | 23:22 |
| blackburn | ok | 23:22 |
| karlnapf | gf wants to have a tea :) | 23:22 |
| karlnapf | take care and good night! | 23:22 |
| blackburn | hah yeah | 23:22 |
| blackburn | good night | 23:22 |
| karlnapf | :) bye | 23:22 |
| -!- karlnapf [~heiko@host86-177-177-13.range86-177.btcentralplus.com] has left #shogun [] | 23:22 | |
| wiking | anybody knows in latex what to do when your limits for sum are not really under and above the sum sign? | 23:38 |
| wiking | ah ok it's \limits | 23:40 |
| blackburn | wiking: not really under?? | 23:41 |
| wiking | $\sum_{a=1}^n$ | 23:41 |
| wiking | it will be not the same as $\sum\limits_{a=1}^n$ | 23:41 |
| blackburn | while it is inlined it would be compact | 23:41 |
| blackburn | there is a way to force \limits there | 23:41 |
| blackburn | some option IIRC | 23:42 |
| -!- PhilTillet [9d9f0a0e@gateway/web/freenode/ip.157.159.10.14] has quit [Ping timeout: 245 seconds] | 23:55 | |
| emrecelikten | Hey guys, do you think it's possible for an undergraduate to write a paper completely on his/her own? | 23:59 |
| --- Log closed Tue Apr 17 00:00:09 2012 | ||
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!