News Archives

Call for papers: ALT 2011

The 22nd International Conference on Algorithmic Learning Theory
Aalto University, Espoo, Helsinki
October 5-7, 2011

CALL FOR PAPERS – ALT 2011

The 22nd International Conference on Algorithmic Learning Theory (ALT
2011, http://www-alg.ist.hokudai.ac.jp/~thomas/ALT11/alt11.jhtml) will
be held at Aalto University in Espoo, Finland, October 5-7, 2011. The
conference is on the theoretical foundations of machine learning. The
conference will be co-located with the 14th International Conference
on Discovery Science (DS 2011, http://ds2011.org/).

Topics of Interest: We invite submissions that make a wide variety of
contributions to the theory of learning, including the following:
* Comparison of the strength of learning models and the design and
evaluation of novel algorithms for learning problems in
established learning-theoretic settings such as
o statistical learning theory,
o on-line learning,
o inductive inference,
o query models,
o unsupervised, semi-supervised and active learning.
* Analysis of the theoretical properties of existing algorithms:
o families of algorithms could include
+ boosting,
+ kernel-based methods, SVM,
+ Bayesian networks,
+ methods for reinforcement learning or learning in
repeated games,
+ graph- and/or manifold-based methods,
+ methods for latent-variable estimation and/or clustering,
+ MDL,
+ decision tree methods,
+ information-based methods,
o analyses could include generalization, convergence or
computational efficiency.
* Definition and analysis of new learning models. Models might
o identify and formalize classes of learning problems
inadequately addressed by existing theory or
o capture salient properties of important concrete applications.

Invited Talks. The two distinguished invited speakers for ALT 2011
are professor Peter Auer (University of Leoben) and professor Jorma
Rissanen (Helsinki Institute for Information Technology). In addition
there will be one invited speaker jointly with DS 2011.

Submission. Authors can submit their papers electronically.
Detailed instructions will be available on the conference web page.

Important Dates.
* Submission deadline: May 18, 2011 (you may submit for as long as
it is May 18, 2011 anywhere in the world)
* Notification of acceptance or rejection will be emailed to the
submitting author by June 30, 2011.
* The camera-ready copy of accepted papers will be due July 10, 2011.

Format. The submitted paper should be no longer than 15 pages in the
standard format for Springer-Verlag’s Lecture Notes in Artificial
Intelligence series. The 15 page limit includes title, abstract,
acknowledgments, references, illustrations and any other parts of the
paper; appendices bypassing the page limit are not allowed.

Policy. Each submitted paper will be reviewed by the members of the
program committee and be judged on clarity, significance and
originality. Joint submissions to other conferences with published
proceedings are not allowed. Papers that have appeared in journals or
other conferences are not appropriate for ALT 2011.

Proceedings. All accepted papers will be published as a volume in the
Lecture Notes in Artificial Intelligence, Springer-Verlag, and will be
available at the conference. Full versions of selected papers of ALT
2011 will be invited to a special issue of the journal Theoretical
Computer Science.

E.M. Gold Award. One scholarship will be awarded to a student author
of an excellent paper (please mark student submissions on the title
page).

Conference Chair: Esko Ukkonen, University of Helsinki, Finland

Programme Committee:
Jyrki Kivinen (Chair), University of Helsinki, Finland
Csaba Szepesvari (Chair), University of Alberta, Canada
Dana Angluin, Yale University
Jean-Yves Audibert, Universite Paris Est
Shai Ben-David, University of Waterloo
Avrim Blum, Carnegie Mellon University
Nader Bshouty, Technion
John Case, University of Delaware
Ricard Gavalda, Universitat Politecnica de Catalunya
Andras Gyorgy, Hungarian Academy of Sciences
Sanjay Jain, National University of Singapore
Gabor Lugosi, Pompeu Fabra University
Remi Munos, INRIA
Ronald Ortner, University of Leoben
John Shawe-Taylor, University College London
Hans Ulrich Simon, Ruhr-Universitat Bochum
Frank Stephan, National University of Singapore
Eiji Takimoto, Kyushu University
Vladimir Vovk, Royal Holloway, University of London
Akihiro Yamamoto, Kyoto University
Sandra Zilles, University of Regina

Local Arrangement Chair: Olli Simula, Aalto University, Finland

Postdoc and PhD studentship at UCD Ireland

A postdoc position and PhD studentship are available in UCD Computer Science funded by IRCSET and IBM under the Enterprise Partnership Scheme.

The work will address the use of machine learning techniques in monitoring Exascale computing systems – see:
http://www.ircset.ie/LinkClick.aspx?fileticket=g3x3srNX0aQ%3d&tabid=243&mid=663

This is part of the Enterprise Partnership Scheme.
http://www.ircset.ie/Default.aspx?tabid=58

Free Computer Vision Software

Philip Torr and Lubor Ladicky have released their code for semantic image segmentation. This code can be used combined object detection, segmentation and depth inference in image sequences and is freely available for academic use only, please visit their project page at http://cms.brookes.ac.uk/staff/PhilipTorr/ale.htm.

ECML/PKDD Discovery Challenge 2011: VideoLectures.Net recommender system

Discovery challenge affiliated with ECML/PKDD 2011 Conference started on the April 18th. It is organized and sponsored by EU project e-LICO and launched via the TunedIT platform. The challenge is related to recommendation of lectures recorded at VideoLectures.Net site and is based on lecture viewing sequences and contents from the site. Best solutions will be awarded with prizes worth 5,500 EUR.

The challenge is organized in order to improve the website’s recommender system. The challenge consists of two main tasks and a “side-by” contest. Due to the nature of the problem, each of the tasks has its own merit: the first task simulates new-user and new-item recommendation (cold-start mode) situation; the second task simulates (normal mode) clickstream based recommendation. A side-by contest is organized for the best computational workflow, to be chosen by an expert panel. The competition will last till 8th July 2011.

For more information and participation please visit ECML/PKDD 2011 Discovery Challenge web page at:
http://tunedit.org/challenge/VLNetChallenge

Important Dates:

* April 18, 2011 – start of the challenge (10:00 AM Central European Time)
* July 8, 2011 – closing of the challenge – participants submit last predictions (11:59 PM Central European Time)
* July 22, 2011 – paper submission deadline
* August 8, 2011 – paper notifications
* August 15, 2011 – camera-ready version due
* September 5, 2011 – workshop

Organizers:

* Matko Bošnjak, Nino Antulov-Fantulin, Tomislav Šmuc – Ruđer Bošković Institute
* Nada Lavrač, Mitja Jermol, Martin Žnidaršič – Jožef Stefan Institute
* Peter Keše – Viidea Ltd

CFP – 2nd Workshop on Applications of Pattern Analysis, deadline 15 June 2011

2nd Workshop on Applications of Pattern Analysis (WAPA 2011)
CIEM, Castro Urdiales, Spain
19 – 21 October 2011
http://www.pascal-network.org/wapa2011

*Workshop Description*

Pattern Analysis and Statistical Learning cover a wide range of technologies and theoretical frameworks, and significant activity in the past years has resulted in a remarkable convergence and many advances in the theory and principles underlying the field.

Bringing these technologies to real world demanding applications is however often treated as a separate problem, one that does not directly affect the field as a whole. It is instead important to consider the field of Pattern Analysis as fully including all issues involved with the applications of this technology, and hence all issues that arise when deploying, scaling, implementing and using the technology.

We call for constributions in the form of Demos, Case Studies, Working Systems, Real World Applications and Usage Scenarios. Challenges may stem from the violation of common theoretical assumptions, from the specific types of patterns and noise arising in certain scenarios, or from the problem of scaling up the implementation of state of the art algorithms to real world sizes, or from the creation of integrated software systems that contain multiple pattern-analysis components.

We are also interested in new application areas, where Pattern Analysis has been deployed with success, and in issues involving the visualisation and delivery and exploitation of the patterns discovered by PA technologies. Systems working in noisy and unstructured environments and situations are particularly interesting.

The goal is to discuss and reward work aimed at making theory useful and relevant, without requesting the researchers to propose new theoretical methods, but rather requesting to show how they solved the many challenges related to applying these methods to real world scenarios, or how they benefited other fields of research. Getting ideas to work in real scenarios is what this is about.

*Call For Papers*

We welcome papers and demos in all of the areas described in the Workshop Description. Papers should be max 7 pages long, in PDF, font size 12, describing a working system that makes use of Pattern Analysis technology and for which interesting challenges were encountered and overcome during its deployment, or an application that has benefited another field of research. Software and Web demos are welcome, as are case studies.

Papers should be submitted on EasyChair
https://www.easychair.org/conferences/?conf=wapa2011

Submission Deadline: 15 June 2011

Proceedings will be published containing the accepted papers within the JMLR Proceedings Series: http://jmlr.csail.mit.edu/proceedings/

*Important Dates*

15 June 2011
Deadline for paper submission

5 August 2011
Notification of Acceptance

19 – 21 October 2011
Workshop

*Organisers*

John Shawe-Taylor
University College London

Tom Diethe
University College London

José L. Balcázar
Universitat de Cantabria, Santander

Cristina Tîrnăucă
Universitat de Cantabria, Santander

Rebecca Martin
University College London

MSc in Computational Intelligence

The University of Sheffield, UK, has launched a new MSc in Computational Intelligence to
start in September 2011.

Computational intelligence is an exciting area that brings together research in engineering,
computing and neuroscience. Recent advances in how the brain works, and applications such
as biologically inspired robotics, have occurred, in large part, due to a greater understanding
of computational intelligence as a unified discipline. This new MSc provides the multi-
disciplinary knowledge and skills to meet the demand for experts in computational
intelligence. The MSc will cover a mixture of modules in computational neuroscience,
machine learning, neural networks, modelling and simulation of natural systems, multi-sensor
data fusion, adaptive intelligence and robotics. Training in research skills will also be
provided and students will undertake a substantial individual project which will allow them
to specialise even further.

For more information or to apply please go to

http://shef.ac.uk/acse/prospectivepg/masters/compintel.html

or contact

Dr Tony Dodd
t.j.dodd(at)shef.ac.uk
+44 (0)114 222 5636

Call for Papers – ICL: Workshop on Iberian Cross-Language NLP tasks

Call for Papers
ICL: Workshop on Iberian Cross-Language NLP tasks
September 7, 2011, Huelva, Spain
in conjunction with the 27th Conference of the Spanish Society for
Natural Language Processing – SEPLN 2011

In the Iberian Peninsula, five official languages co-exist: Basque,
Catalan, Galician, Portuguese and Spanish. Fostering multi-linguality
and establishing strong links among the linguistic resources developed
for each language of the region is essential.

Additionally, a lack of published resources in some of these languages
exists. Such lack propitiates a strong inter-relation between them and
higher resourced languages, such as English and Spanish.

In order to favour the intra-relation among the peninsular languages
as well as the inter-relation between them and foreign languages,
different purpose multilingual NLP tools need to be developed.

TOPICS OF INTEREST

Cross-language / multilingual:

– text categorisation
– information retrieval
– question answering
– patent retrieval
– word sense disambiguation
– opinion mining
– lexical substitution
– text summarization
– text re-use analysis
– plagiarism detection
– paraphrasing for MT
– text similarity estimation
– similarity of Wikipedia across languages

These tasks are often based on statistical, linguistic and
hybrid approaches. Machine translation, cognates exploitation
or semantic relatedness are examples of the multiple resources
available for the development of such tools.

The workshop addresses researchers from different fields of natural
language processing/computational linguistics: text mining, machine
learning, pattern recognition, information retrieval and machine
translation.

IMPORTANT DATES

June 1, 2011 Submission of paper (LNCS format, 6 pages maximum)
July 1, 2011 Notification of acceptance
July 20, 2011 Camera ready due
September 7, 2011 Workshop day

SUBMISSIONS

Please submit your contribution to the ICL’11 workshop via EasyChair
(https://www.easychair.org/conferences/?conf=icl2011). Each submission
will be blind reviewed by at least two members of the Program Committee.
The papers will be published as CEUR Workshop Proceedings.

ORGANISING COMMITTEE

Alberto Barrón-Cedeño, Jorge Civera, Paolo Rosso (Universitat
Politècnica de València)
Marta Vila (Universitat de Barcelona)
Anabela Barreiro (Universidade do Porto)
Iñaki Alegria (Euskal Herriko Unibertsitatea)

PROGRAMME COMMITTEE

Eneko Agirre, Euskal Herriko Unibertsitatea
Amparo Alcina, Universitat Jaume I
Alexandra Balahur, Universidad de Alicante
Yassine Benajiba, Philips Research North America
Davide Buscaldi, Université d’Orléans
Paula Carvalho, Universidade de Lisboa
Paul Clough, University of Sheffield
Víctor Darriba, Universidade de Vigo
Iria da Cunha, Universitat Pompeu Fabra
Arantza Diaz, Euskal Herriko Unibertsitatea
Patrick Drouin, Université de Montreal
Antonio Ferrández, Universidad de Alicante
Jesús Andrés Ferrer, Universitat Politècnica de València
Mikel L. Forkada, Universidad de Alicante
Atsushi Fujita, Future University Hakodate
Miguel Angel García, Universidad de Jaén
Veronique Hoste, University College Ghent
Gorka Labaka, Euskal Herriko Unibertsitatea
François Laureau, Macquarie University
Codrina Lauth, University of Applied Sciences FH Kufstein
Els Lefever, University College Ghent
Evangelos Kanoulas, University of Sheffield
Zornitsa Kozareva, University of Southern California
Antonia Martí, Universitat de Barcelona
Fernando Martínez, Universidad de Jaén
Raquel Martínez, UNED
Mikhail Mikhailov, University of Tampere
Manuel Montes-y-Gómez, INAOE-Puebla
Lidia Moreno, Universitat Politècnica de València
Roberto Paredes, Universitat Politècniva de València
David Pinto, Benemerita Universidad Autónoma de Puebla
Horacio Rodriguez, Universitat Politècnica de Catalanuya
Horacio Saggion, Universitat Pompeu Fabra
Luís Sarmento, Universidade do Porto
Grigori Sidorov, National Polytechnic Institute
Alberto Simões, Universidade do Minho
Sobha L., KBC Anna University Chennai
Thamar Solorio, University of Alabama
Mariona Taulé, Universitat de Barcelona
Dan Tufis, Romanian Academy
Jesús Vilares, Universidade da Coruña
Luís Villaseñor, INAOE-Puebla
Michael Zock, LIMSI-CNRS

PASCAL2 Thematic Programme on Cognitive Inference and Neuroimaging

We would like to draw your attention to the PASCAL2 Thematic Programme
(TP) on “Cognitive Inference and Neuroimaging”. The TP provides the
opportunity to apply for funding of workshops and educational events
that foster collaborations between the domains of neuroimaging and
machine learning. Furthermore, the TP can provide travel stipends for
visits by scientists working in cognitive inference and neuroimaging to
members of PASCAL2.

More information on the TP and how to apply for funding is available at
http://mlin.kyb.tuebingen.mpg.de.

COLT 2011: Call for open problems submission deadline extended

24th Annual Conference on Learning Theory
Budapest, Hungary, July 9-11, 2011
http://colt2011.sztaki.hu

COLT 2011 – Call for Open Problems

Submission deadline is extended to May 11, 2011

The 24th Annual Conference on Learning Theory (COLT 2011) will take place in Budapest, Hungary, on July 9-11, 2011. It will be co-located with the Foundations of Computational Mathematics conference (FOCM 2011, Budapest, July 4th – 14th, 2011).

COLT 2011 will include an Open Problems session. A description of the problems posed will also appear on the conference web site (and in the electronic proceedings).

We encourage everyone to propose and present a clearly defined open research problem (or several closely related open problems), relevant to COLT. Authors should carefully prepare a brief writeup including a clear, self-contained description of the problem, their motivation for studying it, and the current state of this problem (including any known partial or conjectured solutions and relevant references). As last year, we encourage submissions of problems not conventionally in the scope of COLT, as long as there is a convincing reason to include it in the conference. You should be able to clearly express the problem in a 5-10 minute talk. A reward for solving an open problem is encouraged but not required.

If you would like to submit a problem, please email it to colt2011open(at)gmail.com by May 11, 2011. Submissions should be at most 2 pages long and be in the COLT format (.zip, tar.gz).

Deadline is extended to: May 11, 2011
Author notification: May 18, 2011

Open Problems Chair:
Alina Beygelzimer

Harvest Programme Call – Spring 2011

Do you have a good idea for some really cool software, useful and/or
fun for people out there, but you are missing the team, the money, or
the place?

This announcement is for you: read it carefully!

PASCAL2 invites submissions of proposals for Harvest Projects

Important dates

– Expression of intention to submit: May 15, 2011
– Deadline proposal submissions: May 29, 2011
– Notification of acceptance: June 24, 2011

Inquiries: anytime.

There are many innovative things we would be able to do, but we never
find the time, we don’t have the money, students/programmers are
needed and hard to find. Still it would be real fun to devise a smart
code, to see people using it, and to have your name on the Pascal Hall
of Fame 🙂 The Pascal Harvest Programme aims at making it possible,
easy, and rewarded. The main idea behind Harvest is: put together in a
room a team for long enough to produce an innovative software for a
real application. PASCAL2 will pick up the bills.

Sounds interesting? Please check out all you need to know on the
programme website:

(Internal) http://pascallin2.ecs.soton.ac.uk/Programmes/HA/
(External) http://www.pascal-network.org/?q=node/19

For this call we are open to all three scenarios in:

http://pascallin2.ecs.soton.ac.uk/Programmes/HA/harvest_webpage.html#IP
http://www.pascal-network.org/?q=node/19#ipr

————————————————————————

A Harvest project proposal should address the following points in 4-8
pages:

* Problem description: what is the project going to do? Why is it
interesting? Why is Machine Learning relevant?
* Specification and validation. How do we assess performance?
* Expected staffing, location and duration. How many persons will be
needed? For how long?
* Milestones, time-line.
* Requested funding.
* Content of the training, if any, that will be delivered to
participants.

An example proposal can be downloaded from the programme website.
Notice that for this Call we do not expect the team to be
already formed.

Proposals will be evaluated by independent experts. Criteria used in
the evaluation will be:

* Application interest: is this going to be useful to someone?
* State of the art: is the problem still challenging for
scientific/technical/other reasons? Not challenging still not done
yet? Might it lead also to a good paper?
* Impact outside PASCAL: will anyone outside the machine-learning,
optimization and statistics community like it? Can this be viewed
as a generic proof of principle? Of what?
* Training: will junior participants learn interesting and useful
things?
* Management and planning: is the project going to deliver on its
promises?
* Timeliness: can you make this happen soon?

Other things being equal, preference will be given to projects related
to robotics or to cognitive systems, or related to ongoing challenge
or PASCAL Thematic Programmes.

An email stating the intention to submit a proposal should be
addressed to Nicola dot Cancedda at xrce dot xerox dot com and sebag
at lri dot fr by May 15, 2011. Actual submissions should be done
through the PASCAL2 Harvest Programme page by May 29, 2011:

http://pascallin2.ecs.soton.ac.uk/Programmes/HA/Request/

In the meanwhile, prospective proposers are most welcome to create
wiki pages under:

http://pascallin2.ecs.soton.ac.uk/Wiki/HarvestWikiHome

These pages can be used to discuss ideas, attract potential
participants, find a nice host, share interests, divide and conquer a
problem, …

If you have an exciting idea for a project but you are missing the
infrastructure to host it, write it on the wiki and let the programme
organizers know: PASCAL2 is a large network, and maybe someone can
find a place for you. Proposing, organizing, and hosting a Harvest
project will constitute an important contribution to PASCAL2. All such
activity will be taken into account when allocating site funding in
subsequent years.

For all inquiries please write to Nicola dot Cancedda at xrce dot
xerox dot com and sebag at lri dot fr.