REMINDER – CfP: JMLR Special Topic on Kernel and Metric Learning

Multiple Kernel Learning (MKL) has received significant interest in
the machine learning community. It is reaching a point where efficient
systems can be applied out of the box to various application domains,
and several methods have been proposed to go beyond canonical convex
combinations. Concurrently, research in the area of metric learning
has also progressed significantly, and researchers are applying them
to various problems in supervised and unsupervised learning. A common
theme is that one can use data to infer similarities between objects
while simultaneously solving the machine learning task.

A special topic of the Journal of Machine Learning Research will be
devoted to kernel and metric learning with a special emphasis on new
directions and connections between the various related areas; like
learning the kernel, learning metrics, and learning the covariance
function of a Gaussian process. We invite researchers to submit novel
and interesting contributions to this special issue. Further
information can be found at http://doc.ml.tu-berlin.de/jmlr_mkl .

Important dates
===============

Submission: 1 March 2011
Decision: 1 May 2011
Final versions: 1 July 2011

Topics of Interest
==================
Topics of interest include:

* New approaches to MKL, in particular, kernel parameterizations
different than convex combinations and new objective functions
* New connections between kernel, metric and covariance learning,
e.g., from the perspectives of Gaussian processes, learning with
similarity functions, etc.
* Sparse vs. non-sparse regularization in similarity learning
* Efficient algorithms for metric learning
* Use of MKL in unsupervised, semi-supervised, multi-task, and
transfer learning
* MKL with structured input/output
* Innovative applications

Submission procedure
====================
Authors are kindly invited to follow the standard JMLR format and
submission procedure JMLR submission format, the number of pages is
limited to 30. Please include a note stating that your submission is for
the special topic on Multiple Kernel Learning.

Editors
=======
Soeren Sonnenburg, Berlin Institute of Technology, Berlin, Germany
Francis Bach, INRIA and Ecole Normale Superieure, Paris, France
Cheng Soon Ong, ETH, Zurich, Switzerland

Teleconference seminar on the UTL challenge

Learning Data Representations or Similarity Measures:
The UTL Challenge

Teleconference presentation, by Isabelle Guyon
Thursday January 20, 2011, 8 am PT, 11 am ET, 5 pm CET
Participation instructions http://www.afia-france.org/tiki-index.php?page=GroupeDeLecture110120IG (please review them in advance)

Is it possible to LEARN from unlabeled data Representations of Similarity Measures for use in supervised learning tasks? The Unsupervised and Transfer Learning challenge offers an opportunity to explore this problem of fundamental and practical interest.
Labeling data is not only expensive, it is tedious. When it comes to your own personal data it is also something you do not want to outsource. To help us tagging fast our personal pictures, videos, and documents, we need systems that can learn with very few training examples. The question is whether we can exploit similar data (labeled with different types of labels or completely unlabeled) to improve data preprocessing.
This presentation will outline the setup of the challenge and review the state of the art in unsupervised and transfer learning. Potential challenge participants are invited to attend and ask questions.

Prizes: $6000 + free registrations + travel awards
Dissemination: Workshops at ICML and IJCNN; proceedings in JMLR W&CP.
Deadline phase 1 (unsupervised learning): February 28, 2011
Deadline phase 2 (transfer learning): April 15, 2011
Challenge website: http://clopinet.com/ul

Assistant or Associate Professor of Computer Science, Radboud University Nijmegen

Radboud University Nijmegen has an opening for an Assistant or Associate Professor of Computer Science (1,0 fte).

Full details can be found at the following link
http://www.ru.nl/vacatures/details/details_vacature_0?recid=501615

2nd Pascal Challenge on Large Scale Hierarchical Classification

Second Pascal Challenge on
Large Scale Hierarchical Text classification

Web site: http://lshtc.iit.demokritos.gr/
Email: lshtc_info(at)iit.demokritos.gr

Following a successful first edition, we are pleased to announce the 2nd
edition of the Large Scale Hierarchical Text Classification (LSHTC) Pascal
Challenge. The LSHTC Challenge is a hierarchical text classification
competition, using large datasets. This year’s challenge will increase the
scale and the difficulty of the task, using data from Wikipedia
(www.wikipedia.org), in addition to the ODP Web directory data
(www.dmoz.org).

Hierarchies are becoming ever more popular for the organization of text
documents, particularly on the Web. Web directories and Wikipedia are two
examples of such hierarchies. Along with their widespread use, comes the
need for automated classification of new documents to the categories in the
hierarchy. As the size of the hierarchy grows and the number of documents to
be classified increases, a number of interesting machine learning problems
arise. In particular, it is one of the rare situations where data sparsity
remains an issue, despite the vastness of available data: as more documents
become available, more classes are also added to the hierarchy, and there is
a very high imbalance between the classes at different levels of the
hierarchy. Additionally, the statistical dependence of the classes poses
challenges and opportunities for the learning methods.

The challenge consists of three categorization tasks, involving different
documents and category systems. In particular, the largest category system,
based on Wikipedia, contains more than 300,000 categories and 2M documents
for training. The largest category system ever used in the past for
evaluation purposes, to the best of our knowledge, was based on the Yahoo!
Directory and contained 130,000 categories and 500,000 training documents.
In addition to the largest task, two smaller ones, based on Wikipedia and
DMOZ respectively, are included in the challenge. The scale of these is in
the order of the first edition of the challenge. All of the datasets in this
edition are multi-label. Particularly in the two datasets that are based on
Wikipedia, each document is assigned on average to 3.2 and 4.6 categories
respectively. Furthermore, the hierarchies are no longer simple tree
structures, as both documents and subcategories are allowed to belong to
more than one other category. More information regarding the tasks and the
challenge rules can be found at the challenge’s Web site; follow the “Tasks,
Rules and Guidelines” link.

As in the first edition, participants will be able to smoothly and
continuously submit runs, in order to improve their systems. This year we
also plan a two-stage evaluation of the participating methods: one measuring
classification performance and one for computational performance. It is
important to measure both, as they are dependent. The results will be
included in a final report about the challenge and we also aim at organizing
a special ECML’11 workshop.

In order to register for the challenge and gain access to the datasets you
must have an account at the challenge Web site.

Key dates:

Start of testing: January 15, 2011
End of testing: March 31, 2011
Submission of executables and short papers to challenge organizers: April
30, 2011
Submission of workshop papers: May 31, 2010
ECML’11 workshop (subject to approval): September 5, 2011

Organisers:

George Paliouras, NCSR “Demokritos”, Athens, Greece
Eric Gaussier, LIG, Grenoble, France
Aris Kosmopoulos, NCSR “Demokritos” & AUEB, Athens, Greece
Ion Androutsopoulos, AUEB, Athens, Greece
Thierry Artières, LIP6, Paris, France
Patrick Gallinari, LIP6, Paris, France

Unsupervised Learning Challenge

The Unsupervised and Transfer Learning Challenge has started, with $6000 in prizes, free registrations and travel grants.

==> PHASE 1: UNSUPERVISED LEARNING CHALLENGE <== Do you believe that it is possible to LEARN from unlabeled data Representations of Similarity Measures that will then fare well in supervised learning tasks? Now is your chance to prove it: you have 50 days to work on 5 unsupervised learning task from large real world databases. See: http://clopinet.com/ul. There will be publication opportunities at ICML, IJCNN, and in JMLR W&CP. ------------------------------------------------------------------------------------------------------- Timeline: Jan. 3, 2010 Start of phase 1: UNSUPERVISED LEARNING. Datasets made available. No labels available. Feb. 1, 2011 IJCNN 2011 papers due (optional). Feb. 28, 2011 End of phase 1, at midnight (0 h Mar. 1, server time -- time indicated on the Submit page). Mar. 1, 2011 Start of phase 2: TRANSFER LEARNING. Training labels made available for transfer learning. April 1, 2011 IJCNN paper decision notification. April 15, 2011 End of the challenge at midnight (0 h April 16, server time -- time indicated on the Submit page). Submissions closed. April 22, 2011 All teams must turn in fact sheets (compulsory). The fact sheets will be used as abstracts for the workshop(s). Reviewers and participants are given access to provisional rankings and fact sheets. May 1, 2011 Camera ready copies of IJCNN papers due. May 15, 2011 Release of the official ranking. Notification of abstract acceptance. Invitations to submit full paper to JMLR W&CP. June 15, 2011 Invited JMLR W&CP papers due. July 2, 2011 Workshop at ICML 2011, Bellevue, Washington state, USA. To be confirmed. July 31 - Aug. 5, 2011 Special session and workshop at IJCNN 2011, San Jose, California, USA. Confirmed. Aug. 7, 2011 Reviews of JMLR W&CP papers sent back to authors. Sep. 30, 2011 Revised JMLR W&CP papers due.

Three tenure track or tenured positions in Information and Computer Science

Aalto University School of Science (Helsinki, Finland)
invites applications for:

THREE TENURE TRACK OR TENURED POSITIONS IN INFORMATION AND COMPUTER SCIENCE

Aalto University (http://aalto.fi/en/) is a new university created in
2010 from the merger of the Helsinki University of Technology TKK, the
Helsinki School of Economics, and the University of Art and Design
Helsinki. The University’s cornerstones are its strengths in education
and research, with 20,000 basic degree and graduate students, and a
staff of 4,500 of which 300 are professors.

The positions are located at the University’s Department of Information
and Computer Science (http://ics.tkk.fi/en/), and are open to outstanding
individuals who hold a doctorate and have excellent potential for
a successful scientific career. On the basis of their experience and
competence, applicants will be placed at one of the four levels of
the tenure track system: Assistant Professor (1), Assistant Professor (2),
Associate Professor, and (Full) Professor. Successful candidates at
the two first-mentioned levels would be appointed for a fixed term,
whilst appointments at the Associate Professor level are either
permanent (tenured) or for a fixed term. Full Professor positions are
always tenured.

The focus of the Information and Computer Science Department’s
research and teaching activity is on advanced computational methods
for modelling, analysing, and solving complex tasks in technology and
science. The research aims at the development of fundamental computer
science methods for the analysis of large and high-dimensional data
sets, and for the modelling and design of complex software, networking
and other computational systems.

– In the recent Research Assessment Exercise covering all the 46
academic units of Aalto University, the Department was identified as
one of the select two highest-ranking performers (RAE score 24/25)
and as “one of the top five centres in the world in their research
area”. The full report “Striving for Excellence, Aalto University
Research Assessment Exercise 2009” is available at
http://aalto.fi/en/research/rae/.

– The present call for applications covers all areas of information
and computer science compatible with the Department’s research and
teaching mission indicated above. Special consideration will be
given to candidates with research fields complementing and
supporting the current strong areas of the Department. A joint
appointment with the Helsinki Institute for Information Technology
HIIT (http://hiit.fi/) can be negotiated.

The closing date of the call is 4 February 2011. Should there be a
lack of eligible outstanding applicants, the application period may
be extended. While all applicants who have submitted an application
by the deadline will be appropriately considered, Aalto University
reserves the right to consider also other candidates for the announced
positions.

Further details of the positions and the application procedure are available at:

“http://www.aalto.fi/en/current/jobs/professors/professors_information_and_computer_science/” and
“http://dept.ics.tkk.fi/calls/tenuretrack2011/”.

For additional information, please contact Professor Pekka Orponen
(departmental information), tel. +358 9 470 25246, or HR Coordinator
Ilona Kallio (application process), tel. +358 9 470 27286. E-mails:
firstname.lastname(at)aalto.fi.

ECML PKDD 2011 – Call for papers

ECML PKDD 2011 – The European Conference on Machine Learning and
Principles and Practice of Knowledge Discovery in Databases

September 5-9, 2011
Athens, Greece

http://www.ecmlpkdd2011.org/

Key Dates

*********

Abstract submission deadline: April 5, 2011

Paper Submission deadline: April 12, 2011

Paper Acceptance Notification: June 3, 2011

Paper Camera Ready: June 12, 2011

Call For Papers

***************

The European Conference on “Machine Learning” and “Principles and Practice
of Knowledge Discovery in Databases” provides an international forum for
the discussion of the latest high quality research results in all areas
related to machine learning and knowledge discovery in databases and
other innovative application domains.

We invite submissions on all aspects of machine learning,
knowledge discovery and data mining. We especially encourage submissions of
papers that describe the application of machine learning and data mining
methods to real-world problems, and highlight new research challenges in new
domains such as the web, medicine, biology, neuroscience, engineering, government fields.

Submissions that demonstrate both theoretical and empirical rigor are
also highly encouraged.

Proceedings and Special Journal Issues

**************************************

The conference proceedings will be published by Springer Verlag (“Lecture
Notes in Artificial Intelligence Series”).
A selection of papers will be published in two post-conference special issues
of the Springer Verlag journals “Data Mining and Knowledge Discovery” and
“Machine Learning”.

Submissions

***********

All aspects of the submission and notification process will be handled online
via the Microsoft CMT.

The papers must be written in English and formatted according to
the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines.
Authors instructions and style files can be downloaded at:
http://www.springer.de/comp/lncs/authors.html

The maximum length of papers is 16 pages in this format.

Papers submitted should report original work; ECML PKDD 2011 will
not accept any paper which, at the time of submission, is under
review or has already been accepted for publication in a journal
or another conference. Authors are also expected not to submit
their papers elsewhere during the review period.

Papers submitted to ECML PKDD 2011 will normally be reviewed by
minimum of two referees. The review process will be double blind.

Student submissions should be clearly indicated on the submission form.

Conference Organization

***********************

General co-Chairs

Prof. Aris Likas (Univ. of Ioannina, Greece)

Prof. Yannis Theodoridis (Univ. of Piraeus, Greece)

Program Commitee chairs

Prof. Dimitris Gunopulos (Univ. of Athens, Greece)

Dr. Thomas Hofmann (Google Research)

Prof. Donato Malerba (Univ. of Bari, Italy)

Prof. Michalis Vazirgiannis (Athens Univ. of Economics and Business, Greece)

Venue

*****

ECML PKDD 2011 will take place in Athens, Greece. Athens is the capital of
Greece, standing at a strategic point in southeastern Europe,
with unique historical and cultural assets and a location of exceptional
natural beauty, privileged with a perfect weather climate.

Conference Web Page & Social Networking

***************************************

Please visit regularly the conference web page to get the latest updates in
the conference:

http://www.ecmlpkdd2011.org

You may want to join the relevant FACEBOOK group:
http://www.facebook.com/pages/ECML-PKDD-2011/111315008934900

or follow us on TWITTER at: http://www.twitter.com/ECML_PKDD_2011

Open position: researcher in computational biology in Paris

JUNIOR RESEARCHER (TENURE-TRACK) IN COMPUTATIONAL BIOLOGY

The Centre for Computational Biology at Mines ParisTech
(http://cbio.ensmp.fr) develops and applies original mathematical and
computational methods for the processing, modelling and exploitation of
biological, chemical and medical data. Our expertise in machine learning
and statistics is dedicated to solving various challenges in life
science and drug discovery. We have a major focus on cancer research
through a strong partnership with Institut Curie, a leading hospital and
researcher centre dedicated to cancer. We benefit from an exceptional
scientific environment with immediate access to experts in biology and
medicine, modern technological platforms such as sequencing, proteomics,
microarrays or high-content screening, and a number of experts in
mathematics and computer science at walking distance. The laboratory is
located on the Montagne Sainte-Genevieve campus of Institut Curie in
downtown Paris, near Pantheon, at the heart of a rich scientific and
cultural environment.

This position is for a young researcher with exceptional research
potential willing to attack new challenges in computational biology in
an international, open-minded and multidisciplinary environment. The
successful applicant should have a PhD in bioinformatics, mathematics,
computer science or any relevant field, and ideally a post-doctoral
experience on computational biology. He will propose and develop an
original research theme consistent with the laboratory’s research
fields. Projects should combine, where possible, strong methodological
developments and relevant applications in biology and medicine. We are
particularly keen on applications exploiting high-throughput genomic
data to impact cancer research, and would consider favourably a strong
expertise in any relevant domain of applied mathematics or computer
science such as statistics, machine learning, signal processing,
optimization, or discrete mathematics. Collaborations with industrial
partners are strongly encouraged.

The position is on a fixed-term contract, normally leading to a tenure
position within 3 years. To apply please prepare:
– a detailed CV;
– a description of past research work with a list of publications;
– a covering letter and a research project;
– a list of three persons who can be contacted to provide recommendation.

The documents should be sent no later than February 20st, 2011, by
electronic mail to Jean-Philippe.Vert(at)mines.org

Call for papers: WSOM 2011, 8th Workshop on Self-Organizing Maps

Second Call for Papers

for

WSOM 2011, 8th WORKSHOP ON SELF-ORGANIZING MAPS

13 – 15 June 2011, Espoo, Finland
Aalto University School of Science and Technology and
Dipoli Conference Center

Website: http://www.cis.hut.fi/wsom2011

IMPORTANT DATES:

Submission of full papers: January 14, 2011
Notification of acceptance: March 1, 2011
Camera-ready paper and
author registration: April 1, 2011
Advance registration before: April 15, 2011

GENERAL INFORMATION

WSOM 2011 will bring together researchers and practitioners in the
field of self-organizing systems, with a particular emphasis on the
self-organizing maps. It will highlight key advances in these and
closely related fields. WSOM 2011 is the eighth conference in a
series of bi-annual international conferences started with WSOM’97
in Helsinki.

The event will be co-located with the ICANN 2011 conference that
will be organized from 14th to 17th of June, 2011. Conference
programmes, registrations and fees will be coordinated.

PUBLICATION

It is planned that papers accepted for the WSOM 2011 Proceedings
will be published in the Springer series, Lecture Notes in Computer
Science. Registered authors will receive a hard copy proceedings
volume, and the proceedings will be available also in full-text
electronic format via Springer’s internet platform www.springer.com .

VENUE

WSOM 2011 will take place at the Aalto University School of Science
and Technology (former Helsinki University of Technology) and
Dipoli Conference Center. They are located in Espoo, in the close
vicinity of the Helsinki capital area. The area is one of the ICT
research and development hot spots in Europe as well as known for
its beautiful and easily accessible nature. The time of the year is
particularly suitable for visiting Finland.

TOPICS in THEORY, METHODS and APPLICATIONS

We expect contributions related to the theoretical and
methodological aspects of the self-organizing map including:

* Data analysis and visualization with a special topic of
modeling dynamic phenomena
* Various mathematical approaches including information theory
and mathematical statistics
* Software and hardware implementations
* Architectural solutions including hierarchical and growing
networks, ensemble models and special metrics
* Neuro-cognitive studies that compare modeling and empirical
results at different levels

We also call for scientific and practice-oriented papers that
describe the use of self-organizing maps with variants in different
application areas including but not limited to:

* Data mining
* Pattern recognition
* Signal processing
* Knowledge management
* Time series processing
* Industrial applications
* Bioinformatics
* Biomedical applications
* Telecommunications
* Financial analysis
* Cognitive modeling
* Robotics and intelligent systems
* Image processing and vision
* Speech processing
* Language modeling
* Text and document analysis

ORGANIZERS

* Honorary chair
Teuvo KOHONEN
Academy of Finland
* General chair
Timo HONKELA
Aalto University School of Science and Technology
* Program chair
Jorma LAAKSONEN
Aalto University School of Science and Technology
* Local chair
Olli SIMULA
Aalto University School of Science and Technology
* Publicity chair
Jaakko PELTONEN
Aalto University School of Science and Technology

STEERING COMMITTEE

* Teuvo KOHONEN
* Marie COTTRELL
* Pablo ESTEVEZ
* Timo HONKELA
* Jose PRINCIPE
* Helge RITTER
* Takeshi YAMAKAWA
* Hujun YIN

PROGRAM COMMITTEE

* Guilherme BARRETO
* Yoonsuck CHOE
* Jean-Claude FORT
* Tetsuo FURUKAWA
* Colin FYFE
* Barbara HAMMER
* Samuel KASKI
* Krista LAGUS
* Amaury LENDASSE
* Ping LI
* Thomas MARTINETZ
* Risto MIIKKULAINEN
* Klaus OBERMAYER
* Jaakko PELTONEN
* Marina RESTA
* Udo SEIFFERT
* Olli SIMULA
* Heizo TOKUTAKA
* Carme TORRAS
* Alfred ULTSCH
* Marc VAN HULLE
* Michel VERLEYSEN
* Thomas VILLMANN
* Lei XU

====== See http://www.cis.hut.fi/wsom2011 for more details! =======

Two Postdoc Positions in Computer Vision and Machine Learning

Two postdoc position in Computer Vision and Machine Learning are available immediately at
the Institute of Science and Technology Austria (IST Austria) in the group of Christoph
Lampert.

Applicants should hold a PhD and have experience in machine learning, optimization and/or computer vision. Prior knowledge of discriminative machine learning techniques (in particular
kernel methods, structured output learning, and/or probabilistic approaches) will be an
advantage, a strong analytical background is a must. We are looking a for highly motivated
and creative individuals who enjoy working in an excellent research environment including
adequate funding for equipment and conference travel. The successful candidates will have no
mandatory teaching or adminstrative duties, but they should be motivated to take an active
role in the further development of the newly established research group. Good
communication skills and fluency in English are required. German language skills not
required.

Conditions of employment: The post-doctoral positions is provided for one or two years with
the possibility for extension. Salaries are very competitive. The starting dates are flexible.
There is no fixed deadline, applications will be considered until the positions are filled.

Application procedure: Formal applications should include CV, a statement of research
experience and interests, list of publications, academic transscripts, as well as the contact
details of three references. Please send applications as single PDF document to Prof.
Christoph Lampert chl(at)ist.ac.at.

About the institute: IST Austria (www.ist.ac.at) is a new institute that opened its campus near
Vienna in 2009. It is dedicated to basic research in the natural sciences and related disciplines
(http://www.ist.ac.at/research). Established by the Austria Government, IST Austria has
substantial funding, allowing for over 500 employees and graduate students by 2016. The
language of the Institute is English.