2008 Journal club started

Journal club for 2008 started in January, the information is maintained as Events in ML lab.

Thanks to Vinay and Sahely.

The gaussian PDF

Just testing WolverineX (Latex for blogger).

LaTeX for Blogger

To find out how to write LaTeX equations on blogger.. Check this post..

http://wolverinex02.googlepages.com/emoticonsforblogger2

Multiple Instance Learning / Content based Image Retrievel

I will discuss following papers on Wed 11-04-07 at 2.15pm.

1)
@misc{ zhang02contentbased,
author = "Q. Zhang and S. Goldman and W. Yu and J. Fritts",
title = "Content-Based Image Retrieval Using Multiple-Instance Learning",
text = "Q. Zhang, S. Goldman, W. Yu, and J. Fritts. Content-Based
Image Retrieval
Using Multiple-Instance Learning. In The Nineteenth
International Conference on Machine Learning, Sydney, Australia, July
2002.",
year = "2002",
url = "citeseer.ist.psu.edu/zhang02contentbased.html" }

2)
Article title: Support Vector Machines for Multiple-Instance Learning
Author: Andrews, S. Tsochantaridis, I. Hofmann, T.
Journal title: ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS
Bibliographic details 2003, ISSU 15, pages 577-584

Mehul

Semi-Supervised / Transductive Learning

Dear all,

This Wednesday (2:15-3:15 pm) I will be discussing the following paper:

@incollection{NIPS2006_357,
title = {Branch and Bound for Semi-Supervised Support Vector Machines},
author = {Olivier Chapelle and Vikas Sindhwani and Sathiya Keerthi},
booktitle = {Advances in Neural Information Processing Systems 19},
editor = {B. Sch\"{o}lkopf and J. Platt and T. Hoffman},
publisher = {MIT Press},
address = {Cambridge, MA},
pages = {},
year = {2007}
}

The abstract is:

Semi-supervised SVMs (S3 VM) attempt to learn low-density separators by maximizing the margin over labeled and unlabeled examples. The associated optimization problem is non-convex. To examine the full potential of S3 VMs modulo local minima problems in current implementations, we apply branch and bound techniques for obtaining exact, globally optimal solutions. Empirical evidence suggests that the globally optimal solution can return excellent generalization performance in situations where other implementations fail completely. While our current implementation is only applicable to small datasets, we discuss variants that can potentially lead to practically useful algorithms.

Thank You
Rashmin.

Domain Adaptation

Dear all

Continuing our ML Reading Group, this Wednesday (~ 4-5pm) i'll be discussing the following paper:

@inproceedings{Bendavid06Analysis,
author = {Shai Ben-David and John Blitzer and Koby Crammer and
Fernando Pereira},
title = {Analysis of Representations for Domain Adaptation},
booktitle = "Advances in Neural Information Processing Systems 20",
publisher = "MIT Press",
address = "Cambridge, MA",
year = "2007"
}

and the references there in.

Thank You
Saketh.

Introduction to the Group

Blog will keep track of activity in Machine Learning Reading Group at IISc.