| --- Log opened Fri Jan 06 00:00:19 2012 | ||
| CIA-1 | shogun: Sergey Lisitsyn master * ra8869b0 / (13 files): Updated doc of dimensionality reduction toolkit - http://git.io/sAEZjQ | 04:56 |
|---|---|---|
| CIA-1 | shogun: Sergey Lisitsyn master * r2e2788c / (2 files): Fixed typos - http://git.io/8twFuQ | 05:00 |
| -!- blackburn [~qdrgsm@109.226.69.156] has left #shogun [] | 05:00 | |
| -!- blackburn [~qdrgsm@109.226.69.156] has joined #shogun | 14:24 | |
| blackburn | sonne|work: around? | 14:57 |
| blackburn | sonney2k: sonne|work any of you? ;) | 21:01 |
| @sonney2k | blackburn, wassup? | 21:02 |
| blackburn | sonney2k: check dis out http://dl.dropbox.com/u/10139213/shogun/edrt-tutorial.pdf | 21:02 |
| blackburn | should be distributed alongside with my paper :) | 21:03 |
| blackburn | just after I finish it.. | 21:03 |
| @sonney2k | wow | 21:04 |
| @sonney2k | lot of effort | 21:04 |
| blackburn | I told you I want to write a 'book', I guess I started it accidentally | 21:04 |
| @sonney2k | go ahead and do that for the rest of shogun ;-) | 21:04 |
| blackburn | sure, I like this kind of work | 21:04 |
| blackburn | well I love latex | 21:04 |
| blackburn | too much I guess | 21:04 |
| blackburn | sonney2k: where do you think I should include this doc? | 21:06 |
| @sonney2k | blackburn, well we could create shogun/tutorial | 21:07 |
| blackburn | hmm yes sure | 21:07 |
| @sonney2k | and then below that have shogun/tutorial/dimensionreduction | 21:07 |
| blackburn | I'm worried what to include along with paper | 21:07 |
| blackburn | the whole shogun?.. | 21:08 |
| @sonney2k | ? | 21:08 |
| @sonney2k | I don't understand | 21:08 |
| blackburn | sonney2k: jmlr mloss track? | 21:08 |
| @sonney2k | ? | 21:08 |
| blackburn | I need to include software | 21:08 |
| blackburn | my paper.. | 21:08 |
| blackburn | about dim reduction stuff | 21:08 |
| @sonney2k | what is the problem? | 21:09 |
| blackburn | what should I include? | 21:09 |
| blackburn | whole shogun? | 21:09 |
| @sonney2k | I would say yes | 21:09 |
| blackburn | that's pretty strange that's why I'm worried with it | 21:10 |
| @sonney2k | what are the alternatives? | 21:10 |
| @sonney2k | create a big patch file and say - please apply to shogun 1.1.0 ? | 21:10 |
| blackburn | heh | 21:11 |
| blackburn | no alternatives | 21:11 |
| blackburn | sonney2k: can we release 1.1.1 when I finish including this paper stuff? | 21:12 |
| @sonney2k | I would like to have heikos migrations in the next release | 21:13 |
| blackburn | i think it will take 1-2 weeks more | 21:13 |
| blackburn | what is heiko's plan? | 21:14 |
| @sonney2k | btw, I wanted to propose a different way of getting code / patches merged | 21:14 |
| @sonney2k | like you / me also only submitting pull requests | 21:14 |
| @sonney2k | and me/you reviewing them | 21:14 |
| @sonney2k | argh | 21:14 |
| @sonney2k | gtg | 21:14 |
| blackburn | sonney2k: yeah you told it before.. but I still think it will only take our time | 21:15 |
| @sonney2k | it will improve quality - we both make mistakes the other one can spot easily | 21:58 |
| @sonney2k | so it would help - however we should have some hard deadlines until when a patch has to be reviews | 21:59 |
| @sonney2k | e.g. <24hrs | 21:59 |
| @sonney2k | otherwise one is free to merge | 21:59 |
| @sonney2k | blackburn, ^] | 21:59 |
| @sonney2k | ^ | 21:59 |
| blackburn | hmm we should try.. | 22:00 |
| blackburn | sonney2k: could you please take a look on paper 4/5 of my paper? are graphs ok? | 22:01 |
| blackburn | page* | 22:01 |
| blackburn | :D | 22:01 |
| blackburn | paper of paper | 22:01 |
| blackburn | ahaha | 22:01 |
| @sonney2k | blackburn, yes figures look great | 22:03 |
| blackburn | sonney2k: should I enlarge text? | 22:04 |
| blackburn | oh it already takes too much | 22:04 |
| @sonney2k | maybe a bit - but not essential for initial version | 22:04 |
| blackburn | sonney2k: ok thanks | 22:04 |
| @sonney2k | it is good that you renamed it to efficient dim red toolbox | 22:05 |
| @sonney2k | large scale would make many people upset | 22:05 |
| @sonney2k | I know it is fast but it requires the distance matrix to be in memory for most algos | 22:06 |
| @sonney2k | that is a problem | 22:06 |
| blackburn | yeah sure | 22:07 |
| blackburn | well I renamed it because of you told it | 22:07 |
| blackburn | sonney2k: could you please glance over abstract, I reworked it just now? | 22:14 |
| blackburn | sonney2k: btw I mentioned you in acks ;) | 22:22 |
| -!- puneetgoyal [~puneetgoy@117.197.164.241] has joined #shogun | 23:45 | |
| puneetgoyal | blackburn: hi | 23:45 |
| blackburn | puneetgoyal: hi | 23:45 |
| puneetgoyal | blackburn: I am having words such as '98', 'ss' and some more such words or decimals with high tf-idf values | 23:46 |
| puneetgoyal | and I think that is where the problem is | 23:46 |
| blackburn | yes, it could be a problem | 23:47 |
| blackburn | but strange '98' has high tf-idf | 23:48 |
| puneetgoyal | yes, I have checked the alog a lot of times | 23:48 |
| puneetgoyal | actually there are some data files for which charset is some different type | 23:49 |
| puneetgoyal | like CHINESEBIG5 | 23:49 |
| puneetgoyal | and from there such words are coming mainly | 23:50 |
| blackburn | puneetgoyal: well don't care about it now, just try to classify docs | 23:52 |
| --- Log closed Sat Jan 07 00:00:19 2012 | ||
Generated by irclog2html.py 2.10.0 by Marius Gedminas - find it at mg.pov.lt!