PhD Position on Multimodal Semantic Spaces Available

One PhD position/studentship to study integrated text-vision semantic
spaces is available in the Language, Interaction and Computation track
of the 3-year PhD program offered by the Center for Mind/Brain Sciences
at the University of Trento (Italy):

http://www.cimec.unitn.it/

The PhD program (start date: November 2010) is taught in English by an
international faculty. The Language, Interaction & Computation track is
organized by CLIC, an interdisciplinary group of researchers studying
verbal and non-verbal communication using both computational and
cognitive methods:

http://clic.cimec.unitn.it/

CLIC is part of the larger network of research labs focusing on Natural
Language Processing and related domains in the Trento region, that is
quickly becoming one of the areas with the highest concentration of NLP
researchers in Europe.

The studentship is sponsored by a Google Research Award, and the PhD
project will be carried out as a collaboration between CLIC members and
the Zurich Google Research team.

* Project Outline *

The automated measurement of semantic similarity (similarity in meaning)
between words/concepts through unsupervised statistical semantic space
models such as Latent Semantic Analysis or Topic Models has been a
success story in text mining (see Turney and Pantel, 2010, for a recent
survey).

Today, through the Web, we have access to huge amounts of documents that
contain both text and images. While the use of text to improve image
labeling and retrieval is an active and growing area of research (e.g,
Feng and Lapata, 2008, Moringen, 2008, Mathe et al., 2008, Hare et al.,
2008, Olivares et al., 2008, Wang et al., 2009), in this project we want
to go the other way around, and develop novel techniques to extract
multimodal semantic spaces from texts and images, in order to improve
the measurement of semantic similarity among words. On the one hand, it
has been shown (Baroni and Lenci, 2009) that text-extracted conceptual
descriptions are lacking exactly in those aspects (such as color, shape
and parts of objects) that are likely to be most salient in visual
depictions of the same objects. On the other, a recent trend in computer
vision is to represent images as vectors that record the occurrence, in
the analyzed image, of a discrete vocabulary of “visual words” (Yang et
al., 2007, and references there). This development paves the way to the
integration of visual word co-occurrence features into the classic
text-based vectors of current semantic space models.

The topic is expected to have a strong impact both on applied front, as
a breakthrough in the acquisition of large semantic repositories (we
will explore in particular applications to information retrieval), and
from a theoretical point of view, leading to “embodied” models of
computational learning that are more directly comparable to what human
learners do (Barsalou, 2008, Glenberg and Mehta, 2008).

* Application Information *

The successful candidate will have a strong computational background,
including familiarity with machine learning and/or statistical methods,
and should be familiar with the basics of either natural language
processing or (preferably) computer vision. An interest in exploring the
connections between artificial and natural intelligence and cognition is
also desirable.

The official call of the Doctoral School in Cognitive and Brain Sciences
will been announced shortly, and application details will be available
at the page:

http://portale.unitn.it/drcimec/portalpage.do?channelId=-35529

We strongly encourage a preliminary expression of interest in the
project. Please contact Marco Baroni (marco.baroni(at)unitn.it), attaching
a CV in pdf or txt format, or a link to an online CV.

S+SSPR 2010, 17-21 August, Cesme, Turkey. (Call for participation)

Joint IAPR International Workshops on
Structural and Syntactic Pattern Recognition (SSPR 2010)
and Statistical Techniques in Pattern Recognition (SPR 2010)
Cesme, Izmir, Turkey, August 18-20, 2010

http://www.rvg.ua.es/ssspr2010/

A satellite event of the 20th International Conference of Pattern Recognition, ICPR 2010.
Sponsored by IAPR and PASCAL2.

The next joint Statistical Pattern Recognition and Structural and Syntactic Pattern Recognition Workshops (organised by TC1 and TC2 of the International Association for Pattern Recognition, (IAPR) will be held at Cesme Altin Yunus Hotel, Cesme, Turkey prior to ICPR 2010 (which itself will be held in Istanbul). The joint workshops aim at promoting interaction and collaboration among researchers working in areas covered by TC1 and TC2. We are also keen to attract participants working in fields that make use of statistical, structural or syntactic pattern recognition techniques (e.g. image processing, computer vision, bioinformatics, chemo-informatics, machine learning, document analysis, etc.). Those working in areas which can make methodological contributions to the field, e.g. methematicians, statisticians, physicists etc, are also very welcome.

The workshop will be held in Cesme, which is a seaside resort on the Aegean coast of Turkey. There area has many interesting attractions including excellent beaches, interesting fishing villages, and nearby archaeological remains and historical sites. These include Cesme castle and the remains of the ancient Greek city of Erythrae. Cesme can be reached by bus from the airport at Izmir, which has good flight connections to Istanbul.

We have a varied programme including invited talks, regular paper and poster sessions, panel sessions and technical committee meetings.

Confirmed Invited Speakers:
Narendra Ahuja (UIUC)
Ernesto Estrada (University of Strathclyde)
Fatih Porikli (Mithshubishi Electric Research Laboratories)
Luc Devroye (McGill University)

Special Session

SIMILARITY-BASED PATTERN RECOGNITION: CHALLENGES AND PROSPECTS (see below)

Saturday, August 21, 2010

Organisation

General Chair
Edwin Hancock
University of York
E-Mail: erh(at)cs.york.ac.uk

General co-chair
Ilkay Ulusoy
Middle East Technical University, Ankara
E-Mail: ilkay(at)metu.edu.tr

SPR Programme Chair
Terry Windeatt
University of Surrey
E-Mail: t.windeatt(at)surrey.ac.uk

SSPR Programme Chair
Richard Wilson
University of York
E-Mail: Richard.Wilson(at)cs.york.ac.uk

Publicity Chair
Francisco Escolano
University of Alicante
E-Mail: sco(at)dccia.ua.es

………………………………………………………………………………..
Special Session at S+SSPR 2010

SIMILARITY-BASED PATTERN RECOGNITION: CHALLENGES AND PROSPECTS

Saturday, August 21, 2010

Cesme, Izmir, Turkey

Traditional pattern recognition techniques are centered around the notion of “feature”. According to this view, the objects to be classified are represented in terms of properties that are intrinsic to the object itself. Hence, a typical pattern recognition system makes its decisions by simply looking at one or more feature vectors provided as input. The strength of this approach is that it can leverage a wide range of mathematical tools ranging from statistics, to geometry, to optimization. However, in many real-world applications a feasible feature-based description of objects might be difficult to obtain or inefficient for learning purposes. In these cases, it is often possible to obtain a measure of the (dis)similarity of the objects to be classified, and in some applications the use of dissimilarities (rather than features) makes the problem more viable. In the last few years, researchers in pattern recognition and machine learning are becoming increasingly aware of the importance of similarity information per se. Indeed, by abandoning the realm of vectorial representations one is confronted with the challenging problem of dealing with (dis)similarities that do not necessarily obey the requirements of a metric. This undermines the very foundations of traditional pattern recognition theories and algorithms, and poses totally new theoretical and computational questions.

The SIMBAD project is a EU FP7 project which aims at undertaking a thorough study of several aspects of purely similarity-based pattern analysis and recognition methods, from the theoretical, computational, and applicative perspective. It aims at covering a wide range of problems and perspectives, including supervised and unsupervised learning, generative and discriminative models, and its interest ranges from purely theoretical problems to real-world practical applications.

The SIMBAD consortium is planning to hold a half-day meeting on these topics within the S+SSPR Workshop on the morning of Saturday, 21 August 2010. The meeting will contain the following elements:

a) Presentations from the SIMBAD project about methodologies and philosophies in similarity-based pattern recognition, and the challenges it offers as a subfield in pattern recognition;

b) a panel session involving invited speakers;

c) a session of contributed position papers and poster spotlights.

d) a poster session on specific methods and techniques.

Topics of interest for contributed papers include (but are not limited to):

* Foundational issues
* Embedding and embeddability
* Graph spectra and spectral geometry
* Indefinite and structural kernels
* Characterization of non-(geo)metric behavior
* Measures of (geo)metric violations
* Learning and combining similarities
* Multiple-instance learning
* Applications

The workshop aims to explore the spectrum of alternative approaches, methodologies and challenges in the area, rather than detailed techniques. Contributions can be of two kinds:

a) position papers that aim to stimulate discussion of the philosophy of approach underpinning the field,

b) individual technical contributions on a focused topic.

We aim to have a 90 minute oral session devoted to the contributed position papers and together with shorter spotlights for the technical papers. There will be an open poster session for technical papers, with an opportunity to present a five minute “spotlight” talk. Since there is no published proceedings, authors should feel free to provide position papers or posters on previously published work.

Prospective particpants should send a one-page abstract to

Marcello Pelillo (pelillo(at)dsi.unive.it)

by 1st June 2010.

We plan to make the videos of the lectures available on VideoLectures.

ORGANIZERS

Joachim M. Buhmann, ETH Zurich, Switzerland

Robert P. W. Duin, Delft University of Technology, The Netherlands

Mario A. T. Figueiredo, Insituto Superior Technico, Lisbon,

Portugal Edwin R. Hancock, University of York, UK

Vittorio Murino, University of Verona, Italy

Marcello Pelillo, Ca’ Foscari University, Venice, Italy (chair)

PASCAL Visual Object Classes Recognition Challenge 2010

We are running the PASCAL Visual Object Classes Recognition Challenge
again this year. As in 2009 there are 20 object classes for the main
competitions. Participants can recognize any or all of the classes,
and there are classification, detection and pixel-wise segmentation
competitions. This year there is an action classification taster
competition (new for 2010), as well as a taster competition on person
layout (detecting head, hands, feet). There is also an associated
large scale visual recognition taster competition organized by
www.image-net.org.

The development kit (Matlab code for evaluation, and baseline algorithms)
and training data is now available at:

http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/index.html

where further details are given. The timetable of the challenge is:

* 8 May 2010: Development kit (training and validation data plus
evaluation software) made available.

* 31 May 2010: Test set made available.

* 23 August 2010. Deadline for submission of results.

* 11 September 2010: Workshop in association with ECCV 2010, Crete.

Public launch of the iATROS recognition system

The Pattern Recognition and Human Language Technologies group (http://prhlt.iti.es) is proud to announce the public launch of the iATROS recognition system. iATROS is a toolkit that implements preprocessing and feature extraction for speech and handwritten text along with a recognition system based on Hidden Markov Models, N-grams and Finite State models.

iATROS is available from the following web page:

http://prhlt.iti.es/w/iatros

iATROS is implemented as a series of C modules under GPL3 license that can be easily compiled in any Linux environment. iATROS provides standard tools for off-line recognition and on-line speech recognition (based on ALSA modules). iATROS uses HMM on HTK format, N-grams in ARPA format and FSM in PRHLT format. More information is available in the following reference:

Míriam Luján-Mares, Vicent Tamarit, Vicent Alabau, Carlos-D. Martínez-Hinarejos, Moisés Pastor, Alberto Sanchis, and Alejandro Toselli. iatros: A speech and handwritting recognition system. In V Jornadas en Tecnologías del Habla (VJTH’2008), pages 75-78, Bilbao (SPAIN), Nov 2008.

iATROS was implemented in the framework of the iDoc project (TIN2006-15694-C02-01) funded by the Spanish government and FEDER.

Any question or suggestion on the iATROS system can be directed to the e-mail address equipo_iatros@iti.upv.es.

We hope you enjoy using iATROS in your projects!

The iATROS team.

PhD Position on Multimodal Semantic Spaces available

One PhD position/studentship to study integrated text-vision semantic
spaces is available in the Language, Interaction and Computation track
of the 3-year PhD program offered by the Center for Mind/Brain Sciences
at the University of Trento (Italy):

http://www.cimec.unitn.it/

The PhD program (start date: November 2010) is taught in English by an
international faculty. The Language, Interaction & Computation track is
organized by CLIC, an interdisciplinary group of researchers studying
verbal and non-verbal communication using both computational and
cognitive methods:

http://clic.cimec.unitn.it/

CLIC is part of the larger network of research labs focusing on Natural
Language Processing and related domains in the Trento region, that is
quickly becoming one of the areas with the highest concentration of NLP
researchers in Europe.

The studentship is sponsored by a Google Research Award, and the PhD
project will be carried out as a collaboration between CLIC members and
the Zurich Google Research team.

* Project Outline *

The automated measurement of semantic similarity (similarity in meaning)
between words/concepts through unsupervised statistical semantic space
models such as Latent Semantic Analysis or Topic Models has been a
success story in text mining (see Turney and Pantel, 2010, for a recent
survey).

Today, through the Web, we have access to huge amounts of documents that
contain both text and images. While the use of text to improve image
labeling and retrieval is an active and growing area of research (e.g,
Feng and Lapata, 2008, Moringen, 2008, Mathe et al., 2008, Hare et al.,
2008, Olivares et al., 2008, Wang et al., 2009), in this project we want
to go the other way around, and develop novel techniques to extract
multimodal semantic spaces from texts and images, in order to improve
the measurement of semantic similarity among words. On the one hand, it
has been shown (Baroni and Lenci, 2009) that text-extracted conceptual
descriptions are lacking exactly in those aspects (such as color, shape
and parts of objects) that are likely to be most salient in visual
depictions of the same objects. On the other, a recent trend in computer
vision is to represent images as vectors that record the occurrence, in
the analyzed image, of a discrete vocabulary of “visual words” (Yang et
al., 2007, and references there). This development paves the way to the
integration of visual word co-occurrence features into the classic
text-based vectors of current semantic space models.

The topic is expected to have a strong impact both on applied front, as
a breakthrough in the acquisition of large semantic repositories (we
will explore in particular applications to information retrieval), and
from a theoretical point of view, leading to “embodied” models of
computational learning that are more directly comparable to what human
learners do (Barsalou, 2008, Glenberg and Mehta, 2008).

* Application Information *

The successful candidate will have a strong computational background,
including familiarity with machine learning and/or statistical methods,
and should be familiar with the basics of either natural language
processing or (preferably) computer vision. An interest in exploring the
connections between artificial and natural intelligence and cognition is
also desirable.

The official call of the Doctoral School in Cognitive and Brain Sciences
will been announced shortly, and application details will be available
at the page:

http://portale.unitn.it/drcimec/portalpage.do?channelId=-35529

We strongly encourage a preliminary expression of interest in the
project. Please contact Marco Baroni (marco.baroni(at)unitn.it), attaching
a CV in pdf or txt format, or a link to an online CV.

ECML-SUEMA workshop

FIRST CALL FOR PAPERS

European Conference on Machine Learning and Principles and Practice
of Knowledge Discovery in Databases – ECML/PKDD 2010
http://www.ecmlpkdd2010.org/

Workhop on Supervised and Unsupervised Ensemble Methods
and Their Applications – SUEMA 2010
http://suema10.dsi.unimi.it

Barcelona (Spain) 20 September 2010

Dear Colleague, we are pleased to invite you to submit a paper to the
workshop Supervised and Unsupervised Ensemble Methods and Their
Applications (SUEMA 2010), organized in the context of the European
Conference on Machine Learning and Principles and Practice of Knowledge
Discovery in Databases (ECML-PKDD 2010).

The workshop is organized with the support of the PASCAL2 (Pattern Analysis,
Statistical Modelling and Computational Learning) European Network of
Excellence.

This third edition follows up the first one held in Girona (Spain) in
June 2007 (it was the part of the 3rd Iberian Conference on Pattern
Recognition and Image Analysis) and the second one held in Patras
(Greece) in July 2008 (it was the part of the 18th European Conference
on Artificial Intelligence).
SUEMA 2010 intends to provide a forum for researchers in the field
of Machine Learning and Data Mining to discuss topics related to
ensemble methods and their applications.

With best regards

Oleg Okun, Matteo Re and Giorgio Valentini.

More information about the topics of the workshop are available at the
workshop web-site: http://suema10.dsi.unimi.it

— IMPORTANT DATES

Submission 21st June 2010
Notification 12th July 2010
Camera Ready 21st July 2010

— Submission of papers

The authors should submit the papers by e-mail to the workshop chairs
Oleg Okun (olegokun(at)yahoo.com),
Matteo Re (re(at)dsi.unimi.it),
Giorgio Valentini (valentini(at)dsi.unimi.it).

All papers will be peer reviewed based on originality, technical content
and experimental evaluation.

— Workshop Registration

All workshop participants are required to register for the main conference.

— Workshop proceedings

ECML/PKDD will publish all accepted workshop papers on a CD.

As for previous SUEMA editions, workshop chairs are managing to publish
the extended versions of the workshop papers in an edited book or in a
special issue of a machine learning-oriented journal.

The authors will be responsible for producing camera-ready copies of papers,
conforming to the Springer formatting guidelines, for inclusion into the
proceedings. Note that at least one author of each accepted paper is
required to register and attend the workshop in order to present the paper.

—— Main topics

The main topics of the conference include (but are not limited
to):

New ensemble methods raised from new real world supervised and
unsupervised learning problems

Application of ensemble methods in various branches of science
and technology: bioinformatics, medical informatics, computer
security, economics, ecology, meteorology and weather forecast,
image analysis and signal processing, satellite image analysis.

Multi-class, multi-label, multi-path ensemble methods for
hierarchically structured taxonomies.

Fusion of multiple-source/multi-sensor data

Unsupervised ensemble methods for discovering structures in
unlabeled real data

Unsupervised ensemble approaches to assess the
reliability/validity of clusters discovered in real data

Combination techniques and methods to generate multiple base
learners from different features and data

Dynamic member selection for including into an ensemble

Heterogeneous ensembles of base learners

Variants of re-sampling-based methods (bagging, boosting)

Ensemble methods for supervised multi-class classification and
regression

Supervised and unsupervised ensemble methods for structured
domains

Ensemble methods for adaptive incremental learning

— SUEMA Scientific Program Committee

Nicolo’ Cesa-Bianchi, University of Milano, Italy
Carlotta Domeniconi, George Mason University, USA
Robert Duin, Delft University of Technology, the Netherlands
Mark Embrechts, Rensselaer Polytechnic Institute, USA
Ana Fred, Technical University of Lisboa, Portugal
Joao Gama, University of Porto, Portugal
Giorgio Giacinto, University of Cagliari, Italy
Larry Hall, University of South Florida, USA
Ludmila Kuncheva, University of Wales, UK
Francesco Masulli, University of Genova, Italy
Petia Radeva, Autonomous University of Barcelona, Spain
Juan Jose’ Rodriguez, University of Burgos, Spain
Fabio Roli, University of Cagliari, Italy
Paolo Rosso, Polytechnic University Valencia, Spain
Carlo Sansone, Federico II University of Napoli, Italy
Jose’ Salvador Sanchez, University Jaume I, Spain
Grigorios Tsoumakas, Aristotle University of Thessaloniki, Greece
Jordi Vitria’, Autonomous University of Barcelona, Spain
Ioannis Vlahavas, Aristotle University of Thessaloniki, Greece
Terry Windeatt, University of Surrey, UK

CIARP 2010 – Sao Paulo, Brazil (08-11 November)

15th Iberoamerican Congress on Pattern Recognition – CIARP’2010

November 08-11, 2010, São Paulo, Brazil

http://www.ciarp.org/xv/

Contact: ciarp2010(at)ciarp.org

CIARP’2010 will be held in São Paulo, Brazil, from November 8th to
11th, 2010. This conference is organized by the several scientific
associations, including: Cuban Association for Pattern Recognition
(acrp), Advanced Technologies Applications Center (CENATAV),
International Association for Pattern Recognition (IAPR), Mexican
Association for Computer Vision, Neural Computing and Robotics
(MACVNR), Portuguese Association for Pattern Recognition (APRP),
Spanish Association for Pattern Recognition and Image Analysis
(AERFAI), Special Interest Group on Pattern Recognition of the
Brazilian Computer Society (SIGPR-SBC), and Chilean Association for
Pattern Recognition (ChAPR).

This conference will be a forum for the exchange of scientific results
and experiences, as well as the sharing of new knowledge, and the
increasing of the co-operation between research groups in pattern
recognition and related areas.

The CIARP-IAPR Award to the best paper:

We are pleased to announce that an award, consisting of a cash prize
and a certificate, will be given to the author(s) of the Best Paper
registered and presented at CIARP 2010. The aim of this award is to
acknowledge and encourage excellence and originality of new models,
methods and techniques with an outstanding theoretical contribution
and practical application to the field of pattern recognition and/or
data mining. The selection of the winner will be based on the wish of
the author to be considered to the prize, the evaluation and
recommendations from members of the Program Committee and the
evaluation of the CIARP-IAPR Award Committee. This committee,
carefully chosen to avoid conflicts of interest, will evaluate each
nominated paper in a second review process, which will include the
quality of the oral and/or poster presentation.

TOPICS OF INTERESTS

Topics include, but are not limited to:

Applications of Pattern Recognition
Artificial Intelligence Techniques in Pattern Recognition
Bioinformatics
Clustering
Computer Vision
Data Mining
Databases, Knowledge Bases and Linguistic Tools for Pattern Recognition
Discrete Geometry
Document Processing and Recognition
Fuzzy and Hybrid Techniques in Pattern Recognition
Image Processing and Analysis
Kernel Machines
Logical Combinatorial Pattern Recognition
Mathematical Morphology
Mathematical Theory of Pattern Recognition
Medical Imaging
Natural Language Processing and Recognition
Neural Networks for Pattern Recognition
Parallel and Distributed Pattern Recognition
Pattern Recognition Principles
Shape and Texture Analysis
Signal Processing and Analysis
Special Hardware Architectures
Statistical Pattern Recognition
Syntactical and Structural Pattern Recognition
Video analysis
Voice and Speech Recognition

PAPER SUBMISSION

Prospective authors are invited to contribute to the conference by
electronically submitting a full paper in English of no more than 8
pages including illustrations, results and references. The accepted
papers must be presented at the conference in English. All submissions
will be peer reviewed for originality, technical content and relevance
to the theme of this conference by members of the Program
Committee. The final acceptance will be based upon double blind peer
review of the full-length paper.
The accepted papers will be included in the proceedings of the
CIARP’2010, which will be published by Springer in the Lecture Notes
in Computer Science – LNCS.

The papers should be submitted electronically through the submission
option in the CIARP 2010 webpage (http://www.ciarp.org).

The papers should be prepared following the instructions from Springer
LNCS series. (see
http://www.springer.com/sgw/cda/frontpage/0,,5-164-2-72376-0,00.html)

Submission implies the willingness of at least one of the authors to
register and to present the communication at the conference, if it is
accepted.

IMPORTANT DATES

Submission deadline: June 7th 2010
Notification of acceptance: July 10th 2010
Camera ready: August 1st 2010
Conference: November 08-11, 2010

COMMITTEES

* General Co-Chairs:

Isabelle Bloch
—– Telecom ParisTech – CNRS LTCI – Paris, France

Roberto M. Cesar-Jr.
—– University of São Paulo – USP – São Paulo, Brazil

* Organizing Committee

Carlos Hitoshi Morimoto, USP – Brazil
David Correa Martins Jr., UFABC – Brazil
João Eduardo Ferreira, USP – Brazil
Roberto Hirata Jr., USP – Brazil
Ronaldo Hashimoto, USP – Brazil
Yossi Zana , UFABC – Brazil

* Auxiliary Committee

Ana Beatriz V. Graciano, USP – Brazil
Charles Iury, USP – Brazil
Evaldo Oliveira, USP – Brazil
Fabrício Martins Lopes, USP – Brazil
Giseli Ramos, USP – Brazil
Jesus Mena-Chalco, USP – Brazil
Jorge J. G. Leandro, USP – Brazil
Marcelo Hashimoto, USP – Brazil
Thiago T. Santos, USP – Brazil

* Steering Committee.

Alberto Sanfeliu, AERFAI Espana
Alvaro Pardo, APRU Uruguay
Cesar Beltran-Castanon, PAPR Peru
Eduardo Bayro-Corrochano, MACVNR Mexico
Hector Allende, ACHIRP, Chile
Helder Araujo, APRP Portugal
Hemerson Pistori, SIGPR-SBC Brazil
Jose Ruiz-Shulkloper, ACRP Cuba

* Program Committee

TO BE ANNOUNCED

Extended deadline for Call for papers: ICML10 workshop on Machine Learning and Games

Due to numerous requests and to be more in line with the ICML notification deadline, the submission deadline has been extended to April 27. As a result of this, we have also pushed back the acceptance notification to May 20.

Call for papers

MACHINE LEARNING AND GAMES
workshop at ICML 2010

June 25th, 2010
Haifa, Israel

http://www-kd.iai.uni-bonn.de/icml2010mlg/

The primary goal of this workshop is to bring researchers working on various aspects of machine learning and games together. We want to provide a venue for discussing future directions for machine learning in games, both for academia and the industry.

The intention is to keep the scope of the workshop rather broad and include topics such as:
– Learning how to play games well, for games ranging from deterministic and discrete boardgames to non-deterministic, continuous, real time, action oriented games.
– Player/opponent/team modeling, for goals such as improving artificial players in competitive games, mimicing human players, or game or learning curve adaptation.
– Game analysis, for automatic skillranking, matchmaking, or player and team behavior analysis (fraud detection) in multiplayer games.
– Automated content or story generation for games, possibly with attention to user specific constraints and preferences.
– Game adaptivity, e.g. for raising or lowering difficulty levels dependent on the players proficiency, avoiding the emergence of player routines that are guaranteed to beat the game. This topic also includes concerns on game stability and performance guarantees for artificial opponents.
– Novel learning scenarios arising from practical problems in games.
– Machine learning perspectives in/from the games industry.

We will welcome on-going work, position papers, as well as completed work.
Submissions will be reviewed by program committee members on the basis of relevance, significance, technical quality, and clarity. All accepted papers will be presented as posters and among them, eight to ten will be selected for the oral presentation.

The deadline for submission is April 27th, 2010. Submissions should be formatted according to the templates available at the workshop’s website (see above) and submitted via email to icml10mlg(at)iais.fraunhofer.de.

We also invite the authors of relevant, rejected work from ICML to submit their rejected paper together with the reviews generated by the ICML reviewers and an author rebuttal if deemed relevant. These submission should be made as soon as possible after the ICML author notification.

Important dates:
Submissions due: April 27th, 2010
Notification of acceptance:May 20th, 2010
Workshop date: June 25th, 2010

Organizers:
Christian Thurau, Fraunhofer IAIS and B-IT, University of Bonn
Kurt Driessens, Katholieke Universiteit Leuven
Olana Missura, Fraunhofer IAIS and University of Bonn

Extended Deadline: ICML Workshop on Machine Learning Open Source Software 2010

To accomodate researchers waiting for decisions on their ICML papers (due
April 16) before committing to travel to Haifa, the submission deadline for the
Machine Learning Open Source Software (MLOSS) 2010 workshop has been
extended to April 23. As a result of this, we have also pushed back the
acceptance notification to May 8.

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

Call for Contributions

Workshop on Machine Learning Open Source Software 2010
http://mloss.org/workshop/icml10/

at ICML 2010, Haifa, Israel,
25th of June, 2010

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

The ICML workshop on Workshop on Machine Learning Open Source Software
(MLOSS) will held in Haifa, Israel on the 25th of June 2010.

Important Dates
===============

* Submission Date: April 23rd, 2010
* Notification of Acceptance: May 8th, 2010
* Workshop date: June 25th, 2010

Call for Contributions
======================

The organizing committee is currently seeking abstracts for talks
at MLOSS 2010. MLOSS is a great opportunity for you to tell the
community about your use, development, or philosophy of open source
software in machine learning. This includes (but is not limited to)
numeric packages (as e.g. R,octave,numpy), machine learning toolboxes
and implementations of ML-algorithms. The committee will select several
submitted abstracts for 20-minute talks.

The submission process is very simple:

* Tag your mloss.org project with the tag icml2010

* Ensure that you have a good description (limited to 500 words)

* Any bells and whistles can be put on your own project page, and
of course provide this link on mloss.org

On April 23rd 2010, we will collect all projects tagged with icml2010
for review.

Note: Projects must adhere to a recognized Open Source License
(cf. http://www.opensource.org/licenses/ ) and the source code must
have been released at the time of submission. Submissions will be
reviewed based on the status of the project at the time of the
submission deadline.

Description
===========

We believe that the wide-spread adoption of open source software
policies will have a tremendous impact on the field of machine
learning. The goal of this workshop is to further support the current
developments in this area and give new impulses to it. Following the
success of the inaugural NIPS-MLOSS workshop held at NIPS 2006, the
Journal of Machine Learning Research (JMLR) has started a new track
for machine learning open source software initiated by the workshop’s
organizers. Many prominent machine learning researchers have
co-authored a position paper advocating the need for open source
software in machine learning. To date 11 machine learning open source
software projects have been published in JMLR. Furthermore, the
workshop’s organizers have set up a community website mloss.org where
people can register their software projects, rate existing projects
and initiate discussions about projects and related topics. This
website currently lists 221 such projects including many prominent
projects in the area of machine learning.

The main goal of this workshop is to bring the main practitioners in
the area of machine learning open source software together in order to
initiate processes which will help to further improve the development
of this area. In particular, we have to move beyond a mere collection
of more or less unrelated software projects and provide a common
foundation to stimulate cooperation and interoperability between
different projects. An important step in this direction will be a
common data exchange format such that different methods can exchange
their results more easily.

This year’s workshop sessions will consist of three parts.

* We have two invited speakers: Gary Bradski and Victoria Stodden.

* Researchers are invited to submit their open source project to
present it at the workshop.

* In discussion sessions, important questions regarding the future
development of this area will be discussed. In particular, we
will discuss what makes a good machine learning software project
and how to improve interoperability between programs. In
addition, the question of how to deal with data sets and
reproducibility will also be addressed.

Taking advantage of the large number of key research groups which
attend ICML, decisions and agreements taken at the workshop will have
the potential to significantly impact the future of machine learning
software.

Invited Speakers
================

* Gary Bradski One of the main authors of OpenCV. (tentatively
confirmed)

Gary Bradski was previously responsible for the Open Source
Computer Vision Library (OpenCV) that is used globally in
research, government and commercial applications. He has also
been responsible for the open source statistical Machine
Learning Library and the Probabilistic Network Library. More
recently Dr. Bradski led the vision team for Stanley, the
Stanford robot that won the DARPA Grand Challenge autonomous
race in 2005 and most recently helped found the Stanford
Artificial Intelligence Robot (STAIR) project under the
leadership of Professor Andrew Ng. Dr. Bradski recently published
a new book for O’Reilly Press: Learning OpenCV: Computer Vision
with the OpenCV Library.

* Victoria Stodden

Victoria Stodden is a Postdoctoral Associate in Law and a Kauffman
Fellow in Law at the Information Society Project at Yale Law
School. After completing her PhD in statistics at Stanford
University in 2006 with advisor David Donoho, she obtained a
Master in Legal Studies in 2007 from Stanford Law School. She is
developing a new licensing structure for computational research
and author of the award winning paper “Reproducible Research
Standard” that describes her ideas.

Workshop Program
================

The 1 day workshop will be a mixture of talks (including a mandatory
demo of the software) and panel/open/hands-on discussions.

Morning session: 09:00 – 12:00

* Introduction and overview
* Contributed Talks
* Invited Talk: OpenCV (Gary Bradski)
* Contributed Talks
* Discussion: Exchanging Software and Data

Afternoon session: 14:00 – 17:00

* Contributed Talks
* Invited Talk: The Reproducible Research Standard
(Victoria Stodden)
* Discussion: Reproducible research

Program Committee
=================

* Jason Weston (Google Research, NY, USA)
* Leon Bottou (NEC Princeton, USA)
* Tom Fawcett (Stanford Computational Learning Laboratory, USA)
* Sebastian Nowozin (Microsoft Research, UK)
* Konrad Rieck (Technische Universität Berlin, Germany)
* Lieven Vandenberghe (University of California LA, USA)
* Joachim Dahl (Aalborg University, Denmark)
* Torsten Hothorn (Ludwig Maximilians University, Munich, Germany)
* Asa Ben-Hur (Colorado State University, USA)
* Klaus-Robert Mueller (Fraunhofer Institute First, Germany)
* Geoff Holmes (University of Waikato, New Zealand)
* Peter Reutemann (University of Waikato, New Zealand)
* Markus Weimer (Yahoo Research, California, USA)
* Alain Rakotomamonjy (University of Rouen, France)

Organizers
==========

* Soeren Sonnenburg,
Technische Universität Berlin, Franklinstr. 28/29, FR 6-9,
10587 Berlin, Germany

* Mikio Braun
Technische Universität Berlin, Franklinstr. 28/29, FR 6-9,
10587 Berlin, Germany

* Cheng Soon Ong
ETH Zürich, Universitätstr. 6, 8092 Zürich, Switzerland

* Patrik Hoyer
Helsinki Institute for Information Technology,
Gustaf Hällströmin katu 2b, 00560 Helsinki, Finland

Funding
=======

The workshop is supported by PASCAL (Pattern Analysis, Statistical
Modelling and Computational Learning)

Extended Deadline: Special issue of JMLR on Grammar Induction, Representation of Language and Language Learning

Grammar Induction, Representation of Language and Language Learning
– A special issue of Journal of Machine Learning Research –
Extended submission deadline: 3 May 2010

Alex Clark, Dorota Glowacka, Colin de la Higuera, Mark Johnson and John Shawe-Taylor,
guest editors

We would like to invite submissions for a special issue of the Journal
of Machine Learning Research on “Grammar Induction, Representation of
Language and Language Learning”.

We believe now is the time to revisit some of the fundamental grammar/
language learning tasks such as grammar acquisition, language
acquisition, language change, and the general problem of automatically
inferring generic representations of language structure in a data driven
manner.

Though the underlying problems have been known to be computationally
intractable for the standard representations of the Chomsky hierarchy,
such as regular grammars and context free grammars, progress has been
made either by modifying or restricting these classes to make them more
observable or by revisiting these classes with the added insights from
statistical machine learning or optimisation. Generalisations of
distributional learning have shown promise in unsupervised learning of
linguistic structure using tree based representations, access to queries
or using non-parametric approaches to inference. Such approaches are
starting to make inroads into one of the fundamental problems of cognitive
science: that of learning complex representations that encode meaning.

Grammar induction, also known as grammatical inference, was the subject
of an intense study in the early days of Computational Learning Theory,
with the theory of query learning largely developing out of this
research. More recently the study of new methods of representing language
and grammars through complex kernels and probabilistic modelling together
with algorithms such as structured output learning has enabled machine
learning methods to be applied successfully to a range of language
related tasks from simple topic classification through parts of speech
tagging to statistical machine translation.

These methods sometimes rely on more fluid structures than those derived
from formal grammars and yet are able to compete favourably with
classical grammatical models. Furthermore, new approaches have appeared
requiring less significant input from domain experts, often in the form
of annotated data.

Guest editors:
Alex Clark, Royal Holloway, University of London
Dorota Glowacka, University College London
Colin de la Higuera, Nantes University
Mark Johnson, Macquarie University
John Shawe-Taylor, University College London

Submissions:
The journal special issue is aimed at machine learners with an interest
in text modelling and processing who are interested in extending their
work to more complex language tasks, cognitive systems and knowledge
representation moving beyond models that are implicitly or explicitly
based on variants of finite state automata.

Submissions are expected to represent high-quality, significant
contributions in the area of machine learning algorithms and/or
applications of machine learning. Application papers are expected to
describe the application in detail and to present novel solutions that
have some general applicability (beyond the specific application). The
authors should follow standard formatting guidelines for Journal of
Machine Learning Research manuscripts
(http://jmlr.csail.mit.edu/author-info.html). Submissions and reviewing
will be handled electronically using standard procedures for Journal of
Machine Learning Research (http://jmlr.csail.mit.edu/manudb).