IEEE SSCI2011 Symposium Series on Computational Intelligence – Program Available

IEEE SSCI2011 Symposium Series on Computational Intelligence

Paris (France), April 11-15, 2011
http://www.ieee-ssci.org/

General Chair: Bernadette Bouchon-Meunier, LIP6, CNRS-University P. et M. Curie, Paris, France
Honorary chair: Vincenzo Piuri, University of Milan, Italy
Finance Chair: Piero Bonissone, General Electrics, USA
Local Arrangement Chair: Maria Rifqi, LIP6, Université Panthéon-Assas, Paris, France
Web Master: Christophe Marsala, LIP6, Université Pierre et Marie Curie, Paris, France
Publication Chair: Sylvie Galichet, Université de Savoie, France
Publicity Co-chairs: Pau-Choo (Julia) Chung, National Cheng Kung University, Taiwan / Martine De Cock, Ghent University, Belgium / Slawo Wesolkowski, DRDC, Canada
Tutorial, Keynote and Panel Co-chairs: Marios Polycarpou, University of Cyprus, Cyprus / Ali M.S. Zalzala, Hikma Group Limited, Dubai, UAE
Registration chair: Anne Laurent, LIRMM – Université Montpellier 2, France
Poster and local organization: Marcin Detyniecki, LIP6, Université Pierre et Marie Curie, Paris, France
Secretary: Adrien Revault d’Allonnes, LIP6, Université Pierre et Marie Curie, Paris, France

Description:
This international event promotes all aspects of the theory and applications of Computational Intelligence. With its hosting of over thirty technical meetings in one location, it is bound to attract lead researchers, professionals and students from around the world. Sponsored by the IEEE Computational Intelligence Society, the 2011 edition follows in the footsteps of the SSCI 2007 meetings held in Honolulu and of the SSCI 2009 series held in Nashville. The event will take place in the magic town of Paris.

Program
A detailed program of its events (over thirty symposia and workshops, the complete list is below) is now available on the website: http://ieee-ssci.org/2011/program
Please note that SSCI will have 24 keynote speakers and 22 tutorials, spread over most symposia and workshops. This is a unique occasion to have a global outlook on Computational Intelligence and to collect specific expertise.

================================================================================
List of Symposia and Workshops
ADPRL 2011 Symposium on Adaptive Dynamic Programming and Reinforcement Learning
CCMB 2011 Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain.
CIASG 2011 Symposium on Computational Intelligence Applications in Smart Grid
CIBCB 2011 Symposium on Computational Intelligence in Bioinformatics and Computational Biology
CIBIM 2011 Workshop on Computational Intelligence in Biometrics and Identity Management
CICA 2011 Symposium on Computational Intelligence in Control and Automation
CICS 2011 Symposium on Computational Intelligence in Cyber Security
CIDM 2011 Symposium on Computational Intelligence and Data Mining
CIDUE 2011 Symposium on Computational Intelligence in Dynamic and Uncertain Environments
CIFEr 2011 Symposium on Computational Intelligence for Financial Engineering & Economics
CIMI 2011 Workshop on Computational Intelligence in Medical Imaging
CIMSIVP 2011 Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing
CIPLS 2011 Workshop on Computational Intelligence in Production and Logistics Systems
CISched 2011 Symposium on Computational Intelligence in Scheduling
CISDA 2011 Symposium on Computational Intelligence for Security and Defence Applications
CIVTS 2011 Symposium on Computational Intelligence in Vehicles and Transportation Systems
CompSens 2011 Workshop on Merging Fields of Computational Intelligence and Sensor Technology
EAIS 2011 Workshop on Evolving and Adaptive Intelligent Systems
FOCI 2011 Symposium on Foundations of Computational Intelligence
GEFS 2011 Genetic and Evolutionary Fuzzy Systems Workshop
HIMA 2011 Workshop on Hybrid Intelligent Models and Applications
IA 2011 Symposium on Intelligent Agents
IEEE ALIFE 2011 Symposium on Artificial Life
IEEE MCDM 2011 Symposium on Computational Intelligence in Multicriteria Decision-Making
MC 2011 Symposium on Memetic Computing
RiiSS 2011 Workshop on Robotic Intelligence in Informationally Structured Space
SDE 2011 Symposium on Differential Evolution
SIS 2011 Symposium on Swarm Intelligence
T2FUZZ011 Symposium on Advances in Type-2 Fuzzy Logic Systems
WACI 2011 Workshop on Affective Computational Intelligence

LAFLang 2011 – Call for papers

1st International Workshop on Learning, Agents and Formal Languages (LAFLang)
August 22, 2011
Lyon, France

Co-located with the 2011 IEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology

Sponsored by PASCAL 2

http://laflang.wordpress.com/

*AIM *

The workshop focuses on the common space delimited by three main areas: machine learning, agent technologies and formal language theory. The main goal of the workshop is to promote interdisciplinarity among people working in such disciplines, boosting the interchange of knowledge and viewpoints between specialists.

*TOPICS*

We are interested in contributions on any interaction between machine learning, agent technologies and formal language theory. Topics include (but are not limited to):

– Agent systems modelling
– Computational models of language learning
– Theoretical aspects of Grammatical Inference
– Theoretical descriptions of languages based on agent systems
– Formal models of bio-inspired agent systems
– Learning agents: Machine learning and Agent systems
– Applications of machine learning and agent technologies to natural language processing, human-computer interaction and language evolution.
– Intelligent human-computer interaction

*IMPORTANT DATES*

Paper submission deadline: April 4th, 2011
Acceptance notification : June 1st, 2011
Camera ready paper : June 10th, 2011
Workshop : August 22th, 2011

*SUBMISSIONS*

Submitted papers should be 8 pages maximum in length, including figures and references. The paper must be formatted according to the double column style guidelines for A4 papers available here: http://wi-consortium.org/wias/submissionInst.html

All papers should be prepared in pdf format and submitted on the web site for workshop submissions http://liris.cnrs.fr/~wi-iat11/IAT_2011/papers-submission/

*ORGANIZERS*

Leonor Becerra-Bonache, University of Saint-Etienne, France
Gemma Bel-Enguix, Rovira i Virigli Univeristy, Spain
M. Dolores Jiménez-López, Rovira i Virigli Univeristy, Spain

*PROGRAM COMMITTEE*

Dana Angluin, Yale University, USA
Philippe Beaune, ENS Mines Saint-Etienne, France
Leonor Becerra-Bonache, University of Saint-Etienne, France
Gemma Bel-Enguix, Rovira i Virgili University, Spain
Alexander Clark, Royal Holloway University of London, UK
Colin de la Higuera, Nantes University, France
Amaury Habrard, University of Marseille, France
Jeffrey Heinz, University of Delaware, USA
Adrian Horia Dediu, “Politehnica” University of Bucharest, Romania
Jean Christophe Janodet, University of Saint-Etienne, France
María Dolores Jiménez-López, Rovira i Virgili University, Spain
José Oncina, University of Alicante, Spain
Alfonso Ortega, Autonomous University of Madrid, Spain
Marc Sebban, University of Saint-Etienne, France
Menno van Zaanen, Tilburg University, Netherlands
György Vaszil, MTA Sztaki, Hungary

*CONTACT INFORMATION*

If you have any question please feel free to contact us at the following addresses:

leonor.becerra(at)univ-st-etienne.fr
gemma.bel(at)urv.cat
mariadolores.jimenez(at)urv.cat

MLSS Purdue June 2011

The Departments of Statistics and Computer Science at Purdue University
with additional support from Discovery park at Purdue University will
host a Machine Learning Summer School (MLSS, http://mlss.cc) from June
13 (Monday) to June 24 (Friday), 2011. This school is suitable for all
levels, both for people without previous knowledge in Machine Learning,
and those wishing to broaden their expertise in this area. Individuals
without previous knowledge will be able to learn more about the theory
and practice of Machine Learning, while those wishing to broaden their
expertise in this area will find the advanced courses particularly
useful. A partial list of confirmed speakers include:

* Leon Bottou, Microsoft Research
* Talk Title: Large-Scale Machine Learning and Stochastic Algorithms

* William Cleveland, Purdue University
* Talk Title: Divide and Recombine for the Analysis of Large Complex Data sets

* Marina Meila, University of Washington
* Talk Title: Classic and modern data clustering

* Dale Schuurmans, University of Alberta, Canada
* Talk Title: Unified perspectives on supervised, unsupervised and semi-supervised learning

* Satinder Singh (Baveja), University of Michigan, Ann Arbor.
* Talk Title: Reinforcement Learning: From Control to Artificial Intelligence

* Alex Smola, Yahoo! research and Australian National University
* Talk Title: Graphical Models for the Internet

* Ben Taskar, University of Pennsylvania
* Talk Title: Structured Prediction

* Manfred Warmuth, University of California, Santa Cruz
* Talk Title: Recent advances in boosting and online learning

Thanks to generous sponsorship from NSF, AFOSR (support pending),
Computational Design and Innovation Lab, Microsoft Research, IBM
Research, Pascal 2, and Yahoo! a limited number of student scholarships
based on academic merit and need are available (see website for priority
ordering).

The total number of participants will be limited. So please register
early. For information visit our website
http://learning.stat.purdue.edu/wiki/mlss/start

Postdoc position in machine learning/statistics in Potsdam

Research Field: machine learning and statistics
Duration: 18 months
Starting date: as soon as possible
Closing date for applications: 15. April
Payscale: 36.000 EUR per annum and over depending on past experience
(german TVL E13 salary scale)

Applications should be sent to G. Blanchard (department of mathematics,
Potsdam University), preferably in electronic form at the address

gilles.blanchard(at)gmail.com

(please use the tag “[MASH application]” in the subject line)

=== Project description

The MASH project is a research initiative funded by the Seventh
Framework program of the European Union. It brings together five
european institutions in Switzerland, France, Germany and the Czech
republic.

The goal of the MASH project is to investigate and develop new
algorithms and software to enable large groups of individuals to
collaboratively design and combine large families of feature extractors
for several machine learning scenarios (object recognition in images;
goal planning in a simulated environment and with a real-world robotic
arm). The project has started in 2010 and now has an operating
collaborative web platform open to the public (
http://www.mash-project.eu ). External contributors participate to the
project by uploading the source codes of “feature extractors” into the
platform, which are immediately compiled and integrated in the next
starting experiment. The system encourages contributors to improve upon
the work on other and focus on the main weakness of the overall system.

Of crucial interest is the efficient selection and aggregation of
contributed features under a global computational constraint. The
research at the university of Potsdam will concentrate on theoretical
and practical developments of prediction methods from a very large set
of heterogeneous features. In particular selection, aggregation,
grouping and dimension reduction or randomization techniques will be
considered.
Looked after is a relevant expertise in high-dimensional statistics and
machine learning.

The research will be carried out at the University of Potsdam, Germany,
department of mathematics, under the supervision of Prof. G. Blanchard.
The University of Potsdam is situated about 30km southwest of Berlin,
Germany, and has excellent public transportation connection to the capital.

=== Requirements

University degree (PhD or equivalent) in mathematics, computer science
or engineering. We expect from potential candidates very good
programming skills (C++) and strong background in mathematical
statistics, machine learning and/or learning theory.

The Potsdam University is an equal opportunity employer. The goal is to
enhance the percentage of women in the areas where they are
underrepresented. Women, therefore, are particularly encouraged to apply.

CfP: Symposium on Machine Learning in Speech and Language Processing 2011

June 27, 2011
Bellevue, Washington, USA

http://www.ttic.edu/sigml/symposium2011/

The goal of the symposium is to foster communication and collaboration
between researchers in these synergistic areas, taking advantage of
the nearby locations of ACL-HLT 2011 and ICML 2011. It will bring
together members of the Association for Computational Linguistics, the
International Speech Communication Association, and the International
Machine Learning Society.

Topics
=====================

The workshop will feature a series of invited talks and general
submissions. Submissions focusing on novel research are solicited and
we especially encourage position and review papers addressing topics
that are relevant both to Speech, Machine Learning and NLP. These
areas include but are not limited to the use of: SVMs, log-linear
models, neural networks, kernel methods, discriminative transforms,
large margin training, discriminative training, active, semi-
supervised & unsupervised training, structured prediction, Bayesian
modeling, deep learning , and sparse representations. Application
areas include natural language processing, speech recognition,
language modeling, and speaker verification.

Paper Submission
=====================

Prospective authors are invited to submit papers written in English
via the “Submissions” link on the symposium website
http://www.ttic.edu/sigml/symposium2011/. Each paper will be reviewed
by at least two reviewers, and each accepted paper must have at least
one registered author.

Confirmed Speakers
=====================

Yoshua Bengio, Jeff Bilmes, Ming-Wei Chang, Stanley Chen, Sanjoy
Dasgupta, Mark Hasegawa-Johnson, Bhuvana Ramabhadran, George Saon,
Lawrence Saul, and Mark Steedman.

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

April 15, 2011 Papers due
May 6, 2011 Notification of acceptance
May 27, 2011 Deadline for registration
June 27, 2011 Symposium
Venue, Accommodation and Registration

Organizing Committee
=====================

Hal Daume III University of Maryland
Joseph Keshet TTI-Chicago
Dan Roth UIUC
Geoffry Zweig Microsoft

Scientific Program Committee
=====================

Jeff Bilmes University of Washington
Brian Kingsbury IBM
Karen Livescu TTI-Chicago

2 Postdoc Positions in Machine Learning at INRIA Lille

The SEQUEL (Sequential Learning) lab of INRIA Lille, France, https://sequel.lille.inria.fr/ is seeking to appoint two Postdoctoral Fellows.

The positions are funded by the newly launched European COMPLACS project (Composing Learning for Artificial Cognitive Systems) http://www.csml.ucl.ac.uk/projects/complacs/
and also the french EXPLO-RA project (Exploration-Exploitation for Efficient Resource Allocation. Applications to optimization, control, learning, and games) http://sites.google.com/site/anrexplora/Home

We welcome applicants with a good mathematical background who are interested in working on such topics as bandit algorithms, sequence prediction, learning in Markovian environments, reinforcement learning, game theory, non-parametric statistics of time series, and/or related topics.

The research will be conducted under the supervision of Remi Munos, Mohammad Ghavamzadeh, Daniil Ryabko, and Alessandro Lazaric.

The positions are research only and are for two years, with the possibility of being extended. The starting date is flexible and can be as early as needed.

INRIA is France’s leading institution in Computer Science, with over 2800 scientists employed, of which around 250 in Lille. Lille is the capital of the north of France, a metropolis with 1 million inhabitants, with excellent train connection to Brussels (30 min), Paris (1h) and London (1h30).

The Sequel lab is a dynamic lab at INRIA with over 25 researchers (including PhD students) which covers several aspects of machine learning from theory to applications, including statistical learning, reinforcement learning, and sequential learning.

Candidates must have a Ph.D. degree (by the starting date of the position) in computer science, statistics, or related fields, possibily with background in reinforcement learning, bandits, games, or optimization.

To apply please send a CV to remi.munos(at)inria.fr or mohammad.ghavamzadeh(at)inria.fr, or daniil.ryabko(at)inria.fr, or alessandro.lazaric(at)inria.fr

Lecturer position at University of Glasgow

Ref: E20074

Salary: Grade 7 £31,798 – £35,788 / Grade 8 £39,107 – £45,366

Help develop and enhance the research profile of the School of Computing Science by undertaking Statistical Inference and Machine Learning research within the Inference, Dynamics and Interaction research group. Apply advanced Bayesian inference techniques and computational techniques such as MCMC to real world problems. Responsible for high quality teaching at undergraduate and postgraduate level; contribute to ongoing development and design of the curriculum, in a manner that supports a research-led approach to student learning.

For more information, contact: Roderick.Murray-Smith(at)glasgow.ac.uk

Apply online at http://www.gla.ac.uk/about/jobs/

Closing date: 15th April 2011.

CFP: ICML 2011 Workshop on On-line Trading of Exploration and Exploitation 2

ICML 2011 Workshop on On-line Trading of Exploration and Exploitation 2
2 July 2011, Bellevue, Washington, USA

URL: http://explo.cs.ucl.ac.uk/workshop/
Deadline for submission: 28 April 2011

Workshop description
——————————
On-line problems such as website optimisation require to trade exploration and exploitation in order to learn and optimise an unknown target. For instance, in the Pascal Exploration & Exploitation Challenge 2011, a web server observes clicks from visitors to a webpage, and aims to maximise the ratio of clicks per page views. The relationship between the visitor-content pairs and clicks is unknown but it can be learnt from past observations. The content presented to the visitors is either chosen to improve our model of clicks in regions of uncertainty or it is based on the model that has been built so far. These two distinct motives are referred to as exploration and exploitation. Thus, the web server should explore enough to be able to build an accurate model of the visitor’s behaviour, while allowing for sufficient exploitation in order to earn clicks.

The problem of trading exploration and exploitation was first tackled in the “multi-armed bandit” formalism, in which the target observations are compared to rewards obtained when pulling arms of slot-machines. The first theoretical analysis focused on independent reward distributions for each arm. However, in a real-world scenario, arms (inputs) are rarely independent and modelling the dependencies is essential in order to obtain the best learning rate. Gaussian Processes (GP), for instance, are a powerful modelling tool that has been widely used in bayesian online optimisation, in combination with heuristics such as the Most Probable Improvement for selecting inputs where to sample the function. However, performance guarantees for the use of GP in a bandit setting were only found in 2010, when used in combination with the Upper Confidence Bound heuristic for trading exploration and exploitation (Srinivas et al., 2010).

The exploration/exploitation dilemma is a recurrent topic in many areas of research, e.g. global optimisation, reinforcement learning, tree search, recommender systems or information retrieval. The trading of exploration and exploitation is particularly of high importance in various large-scale applications, such as sponsored search advertising (Graepel et al., 2010) or content-based information retrieval (Auer at al., 2010), where the aim is to help users quickly access the information they are looking for. The workshop will provide an opportunity to present, compare and discuss the performance of different exploration/exploitation techniques as well as theoretical analysis of such algorithms. A particular focus of the workshop will be large scale applications. The results of the Exploration and Exploitation Challenge will also be presented during the workshop.

Call for papers
——————————
The workshop will be single-day, comprising of invited talks and presentations of contributed work, with time for discussion. Depending on quality and compatibility with the workshop objectives, slots for brief talks and posters will be allocated.

We invite contributions on the topic of trading exploration and exploitation in various domains including (but not limited to) bandit games, online optimisation, reinforcement learning, tree search, recommender systems, information retrieval, etc. Topics of interest include: applications and practical performance of techniques to trade exploration and exploitation, benchmark/comparison of different techniques, computational challenges in large scale applications, new techniques, theoretical analyses, etc.

Contributions should be communicated to the programme committee (the organisers) in form of an extended abstract (from 4 to 8 pages in the ICML conference paper style), sent by email to: louis.dorard(at)gmail.com .

Important dates
——————————
28 April 2011 – Deadline for abstract submission
20 May 2011 – Notification of Acceptance
2 July 2011 – Workshop taking place in Bellevue, Washington, USA

Workshop organisers
——————————
Louis Dorard, University College London
Suzanne Weller, Adobe
John Shawe-Taylor, University College London
Dorota Glowacka, University College London

Point of contact
——————————
Louis Dorard: louis.dorard(at)gmail.com

The workshop is supported by the Pascal Network of Excellence.

Call for Posters: CVPR’11 Workshop on Fine-Grained Visual Categorization (FGVC)

Deadline for Submission: April 1, 2011 (23:59 GMT)
Notification of Acceptance: Early May, 2011 (4 or 5-week review period)
Workshop date: June 20, 24 or 25, 2011
Website: http://www.fgvc.org

Overview:
Fine categorization, for example the fine distinction into species of
animals and plants, of car and motorcycle models, of architectural
styles, etc., is one of the most interesting and useful open problems
that the machine vision community has yet to confront. Aspects of fine
categorization (also referred to as “subordinate categorization” in
the psychology literature) are discrimination of related categories,
taxonomization, and discriminative vs. generative learning.

Fine categorization lies in the continuum between basic level
categorization (frog vs piano) and identification of individuals (face
recognition, biometrics). The visual distinctions between similar
categories are often quite subtle and therefore difficult to address
with today’s general-purpose object recognition machinery. It is
likely that radical re-thinking of some of the matching and learning
algorithms and models that are currently used for visual recognition
will be needed to approach fine categorization.

This workshop will explore computational questions of modeling,
learning, detection and localization. The invited talks, including
researchers from psychology and psychophysics, will shed light on
human expertise and human performance in subordinate categorization
and taxonomization.

Topics of interest include the following:
– Novel datasets for fine-grained categorization
– Appropriate error metrics for fine-grained categorization
– Constructing field-guides for visual categories
– Embedding human experts’ knowledge into computational Models
– Fine-grained categorization with humans in the loop
– Attribute-based techniques for fine-grained categorization
– Using taxonomies to improve fine-grained categorization
– Part-sharing models for categorization/recognition
– Zero-shot/one-shot recognition
– Transfer-learning from known to novel subcategories
– Domain-specific techniques that generalize to various other domains
– Unsupervised subcategory discovery
– Learning of discriminative features for fine-grained categorization
– Multimodal (e.g. combined audio/video) techniques for fine-grained
categorization

Submission and Reviews:
We invite submission of 1.5-2 page extended abstracts describing work
in the domains suggested above or closely-related areas. Accepted
submissions will be presented as posters (standard CVPR poster format)
at the workshop. Authors are invited to submit a draft or sketch of
the poster’s contents as an optional 3rd page. The extended abstract
and poster sketch should be submitted as a single PDF file with no
more than 3 pages. We also invite authors of accepted CVPR’11 papers
submit an extended abstract of their work to the workshop. Reviewing
of abstract submissions will be carried out by the Program Committee
and will be double-blind.

More information can be found on the FGVC website: http://www.fgvc.org

Symposium on Machine Learning in Speech and Language Processing

June 27, 2011
Bellevue, Washington, USA

http://www.ttic.edu/sigml/symposium2011/

The goal of the symposium is to foster communication and collaboration between researchers
in these synergistic areas, taking advantage of the nearby locations of ACL-HLT 2011 and
ICML 2011. It will bring together members of the Association for Computational
Linguistics, the International Speech Communication Association, and the International
Machine Learning Society.

Topics
=====================

The workshop will feature a series of invited talks and general submissions. Submissions
focusing on novel research are solicited and we especially encourage position and review
papers addressing topics that are relevant both to Speech, Machine Learning and NLP. These
areas include but are not limited to the use of: SVMs, log-linear models, neural networks,
kernel methods, discriminative transforms, large margin training, discriminative training,
active, semi- supervised & unsupervised training, structured prediction, Bayesian modeling,
deep learning , and sparse representations. Application areas include natural language
processing, speech recognition, language modeling, and speaker verification.

Paper Submission
=====================

Prospective authors are invited to submit papers written in English via the “Submissions” link
on the symposium website http://www.ttic.edu/sigml/symposium2011/. Each paper will be
reviewed by at least two reviewers, and each accepted paper must have at least one registered
author.

Confirmed Speakers
=====================

Yoshua Bengio, Jeff Bilmes, Ming-Wei Chang, Stanley Chen, Sanjoy Dasgupta, Mark
Hasegawa-Johnson, Bhuvana Ramabhadran, George Saon, Lawrence Saul, and Mark
Steedman.

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

April 15, 2011 Papers due
May 6, 2011 Notification of acceptance
May 27, 2011 Deadline for registration
June 27, 2011 Symposium

Organizing Committee
=====================

Hal Daume III University of Maryland
Joseph Keshet TTI-Chicago
Dan Roth UIUC
Geoffry Zweig Microsoft

Scientific Program Committee
=====================

Jeff Bilmes University of Washington
Brian Kingsbury IBM
Karen Livescu TTI-Chicago