Reading groups this year & paper pool

As a result of today's meeting what is agreed is actually to continue on the light reading group format with some small modifications:

1. We will have a reading group every two weeks
2. We will have a pool of papers to read and we will select one paper from that pool for every reading group. (To initiate this pool of papers, please write your paper suggestions as a comment to this post - send at least one paper suggestion until February 5)
3. Everybody will make their best to come to the reading group by reading the paper.
4. We will continue to the blog posts and google calendar entries for communication. You can setup your google calendar so that you receive reminders for every new entry.

So basically nothing has changed with respect to the last year except than the pool of papers. For me, last year's light reading groups were not that effective. If at one point we feel the same, then we will discuss again.

Another thing, at the meeting at some point it is said that "if nobody likes the paper the presenter will change it". I now think that maybe this is not a good idea. We should count on each others decision and read the paper anyway.

The ones who would like to have a heavy reading group will make a separate meeting.

Lastly, the first reading group will be on 12 February. Along with your paper suggestions please also say if you would like to be the first one.

oya

meeting for reading groups - 26 Jan @ 14:00

Hi,

I guess everybody is back to work again after the long break and we can restart our reading groups.

To organize the reading groups this year and to discuss what kind of readings we would like to have, let's have a meeting this tuesday. I hope (almost) everybody is available on Tuesday 14:00 next week (26 Jan 2010). If not, we'll find another time.

The main discussion will be on the format, the topics we would like to cover, whether or not to continue with the light and heavy ones, the frequency of the reading groups, ....

If you won't make it to the meeting, you can email your comments to me.

best,
oya

Next Heavy Reading group

Next reading group will take place on:

11 December 2009

Presented by:

Oya Aran

Paper to read:

Gaussian Process Classification for Segmenting and Annotating Sequences
Altun, Hofmann & Smola
http://www.cs.brown.edu/~th/papers/AltHofSmo-ICML2004.pdf

This will be the last reading group of the year. We will continue the reading groups next year, on mid January, when everybody is back from holidays.

Next Heavy Reading Group

Next reading group will take place on:
Thurs. Dec 3rd at 11am

Presented by:
Kate

Paper to read:
Dynamic Topic Model:
www.cs.princeton.edu/~blei/papers/BleiLafferty2006a.pdf

Next light reading roup: The Combining Classifier: to Train or Not to Train?

Next reading group will take place on:

27 November 2009

Presented by:

Oya Aran

Paper to read:

The Combining Classifier: to Train or Not to Train? by R. Duin
/homes/oaran/Public/papers/duin02combining.pdf

Weighted Kappa: Nominal Scale Agreement with provision for scaled disagreement or partial credit Jacob Cohen, Psychological Bulletin,1968

Next Light reading group will take place on:

6th November

Presented by:

Hayley

Paper to read:

Weighted Kappa: Nominal Scale Agreement with provision for scaled disagreement or partial credit Jacob Cohen, Psychological Bulletin,1968
/home/userdirs/hhung/E000783444_1.pdf

This paper should be useful to a number of people who may be collecting any type of human annotations.

Suggestion for heavy reading group themes

In continuation of the CRF topic and also concurrently with the dynamic topic models paper we were reading, I suggest that we find a nice tutorial on gaussian processes,
or maybe even spice up the reading group by doing a 'watching group' for next time:
http://nips.cc/Conferences/2006/Program/event.php?ID=4
There's also a text book online by the presenter here:
http://www.gaussianprocess.org/gpml/chapters/

Following on from this, we can continue Kate's paper on dynamic topic models and after this combine what we've learnt from Gaussian processes with CRFS with this paper:
http://www.cs.brown.edu/~th/papers/AltHofSmo-ICML2004.pdf

I haven't read/seen any of this stuff yet so I have no idea whether it would be any good. However, they are by good people and so my gut reaction is that this would be quite a nice theme to continue.

Let me know what you think!