PhD Scholarships – IMT Institute for Advanced Studies

IMT Institute for Advanced Studies Lucca (www.imtlucca.it) is accepting applications, from extremely motivated students oriented towards dynamic and highly applicative research opportunities, for fully-funded positions in its
2013 Doctoral Research Program.

The Track in Computer, Decision, and Systems Science (CDSS) aims to equip researchers and professionals with a wide knowledge of the theoretical foundations of computer science, informatics and system analysis that are applicable to a large variety of real-life problems of industrial, managerial, economic, and societal interest. Such elements include control systems, management science, optimal decision making and numerical optimization, image analysis and pattern recognition. The objective of the program is to provide Ph.D. candidates with the necessary scientific competence to master the theoretical aspects of the discipline, to propose original research ideas, and to develop numerical algorithms, managerial solutions and software tools for applying the new concepts to practical applications.

The Track in Computer, Decision and Systems Science is organized into four
curricula:

Computer Science (CS)
The curriculum in Computer Science (CS) focuses on key aspects of informatics, such as open-endedness, autonomy, security, concurrency, cost-effectiveness, quality of services, and dependability. The main goal is to study models, algorithms, and verification methods for modern distributed systems. The doctoral students enrolled in this curriculum will acquire extensive knowledge of the fundamentals and applications of architectures and languages for such distributed systems, including global and grid cloud computing systems, web systems and services, embedded systems, web data mining, and mobile systems. They will also learn professional skills for the application of computer technologies to wide area networks.

Control Systems (SYS)
The curriculum in Control Systems (SYS) is oriented towards model-based control of dynamical systems and decision-making algorithms, including embedded optimization algorithms for control and management of stochastic, networked, and large-scale dynamical systems. Motivated by the pervasive nature of data information systems and by the availability of powerful (and possibly distributed) computational resources, the main goal is to devise complex decision-making strategies that make systems react with a certain degree of autonomy and in an intelligent way to changes in their operating environment. Research skills in model-based control and optimization of dynamical systems taught enable students to conceive novel theories and algorithms. Students also learn professional skills for designing, simulating, and deploying control systems in a variety of application areas, such as smart grids and energy markets, finance, automotive and aerospace systems, water network management, industrial processes and many others.

Image Analysis (IA)
The curriculum in Image Analysis (IA) focuses on the analysis of large-scale multimodality imaging data for life sciences. Motivated by the explosion in biomedical imaging data, the goal is to develop high-throughput and high-precision strategies to analyze intelligently these vast data sets to prove clinically-driven hypothesis and unearth unseen patterns. Such vast datasets arise from studies of various organs (heart, brain and vasculature) and organisms (humans, other model organisms such small or large animals, and plants), using multiple modalities (MRI, PET, and optical at various scales), which span multiple dimensions (2D, 3D, monotone and multispectral), and are dynamic and repeated. This scenario is particularly prevalent now, where this type of analysis is needed to speed up phenotyping studies that accompany genotype-driven experiments.

Management Science (MS)
The curriculum in Management Science (MS) is oriented towards managerial decision making in complex organizations based on a quantitative approach to finance, marketing, information systems, operations, organizational behavior, innovation and industrial dynamics. Track participants are expected to acquire a solid grasp of underlying principles of information theory, decision sciences, statistics and numerical methods, along with their organizational and economic implications. Students and faculty address research questions raised by the emerging digital economy, the transformation of organizations and markets, and opportunities for new business models. MS is inherently multi-disciplinary. Study in this area utilizes faculty with backgrounds in economics, management science, computer science, decision sciences and complex system analysis. Although the program is primarily designed to prepare candidates for leading academic positions in top business and industrial engineering schools, a number of our graduates also assume high-level consulting or other industry positions.

Each student is invited to construct a personal study plan with Advisor, drawing from entire range of course offerings, to best suit his or her background and research interests.

Please visit the call website
(http://www.imtlucca.it/phd/call_for_applications/index.php) for more details regarding program content, the numerous benefits that students enjoy (including scholarships and room and board), and for the online form.

Please apply online ONLY by September 26th 2012.

IMT is also accepting applications in the fields of:

• Economics
• Management and Development of Cultural Heritage
• Political History

Those interested will be able to hear a real-time presentation of the program on an interactive webinar scheduled for June 28th 2012 (after this date a recording of the same will be available for viewing). To sign up, go to www.brightrecruits.com/webinars.

Follow us on Facebook, LinkedIn and YouTube.

Human Activity and Vision Summer School

– Monday 1st to Friday 5th of October 2012
– INRIA, Sophia-Antipolis/Nice on the French Riviera
– website:
http://www.multitel.be/events/human-activity-and-vision-summer-school

== Overview

The Human Activity and Vision Summer School will address the broad domains of human activity modeling and human behavior recognition, with an emphasis on vision sensors as capturing modality. Courses will comprise both tutorials and presentations of state-of-the-art methods by active researchers in the field.

The goal of the courses will be to cover most of the whole human activity analysis chain, starting from the low level processing of videos and audio for detection and feature extraction, to medium level (tracking and behavior cue extraction) and higher level modeling and recognition using both supervised and unsupervised techniques.
Applications of the different methods to action and activity recognition in different domains ranging from Activities of Daily Living to surveillance (individual behavior recognition, crowd monitoring) will be considered.

Presentation of real uses cases, market needs, and current bottlenecks in the surveillance domain will also be addressed, with one half day devoted to presentations and panel discussions with professional and industrial presenters.

See list of topics and speaker below.

== Audience

The summer school is open to young researchers (in particular master or Ph.D. students) and researchers from both the academia and industry working or interested in the human activity analysis domain or connected fields like surveillance.

== Application/Registration

The registration is Euros 300. This includes all the courses, coffee breaks and lunch. The fee does not include accommodation or dinners.

A limited number of cheap accommodations for students are available.
To apply for a position at the Summer School and find more practical information, please go to:
http://www.multitel.be/events/human-activity-and-vision-summer-school

== List of topics and confirmed speakers

* Object detection and tracking
– Francois Fleuret (Idiap Research Institute)
– Alberto del Bimbo and Federico Pernici (Università di Firenze)
– Cyril Carincotte (Multitel)
– Jean-Marc Odobez (Idiap research Institute)

* Crowd analysis and Simulation
– Mubarak Shah (University of Central Florida)
– Paola Goatin (INRIA)
– Cyril Carincotte (Multitel)

* Action and behavior recognition
– Ivan Laptev (INRIA)
– Ben Krose (University of Amsterdam)
– Francois Bremond (INRIA)

* Social Behavior Analysis
– Elisabeth Oberzaucher (University of Vienna)
– Hayley Hung (University of Amsterdam)

* Unsupervised activity discovery and active learning
– Tao Xiang (University of Queen Mary)
– Jean-Marc Odobez and Remi Emonet (IDIAP)

* Body and head Pose estimation
– Cheng Chen (Idiap Research Institute)
– Guillaume Charpiat (INRIA)

* Audio processing
– Maurizio Omologo (Foundation Bruno Kessler)
– Bertrand Ravera (Thales Communication France)

Call for papers: The 4th BMVC UK Students Workshop (BMVW)

Guildford, Surrey, 07 September 2012
http://bmvc2012.surrey.ac.uk/workshop.php

Note for PASCAL members: BMVC is a PASCAL sponsored event and the talks will be recorded by VideoLectures.net.
We’re requesting additional PASCAL sponsorship for this workshop on its own and plan to have invited speakers and to offer free workshop registration for PASCAL members if the sponsorship application is successful.

IMPORTANT DATES

* Submission deadline: 13 July 2012
* Notification of acceptance: 27 July 2012
* Camera ready papers: 11 August 2012
* Workshop: 07 September 2012

The BMVC Students’ Workshop is run in conjunction with the main BMVC 2012 conference organised by the British Machine Vision Association. This workshop has now become a regular feature of BMVC to give students in computer vision an opportunity to network and start collaborations at an early stage in their research career.

Students studying in the UK are invited to submit full-length high-quality papers of which the main author is a student. All papers will be reviewed and selected for either oral or poster presentation.
*Oral presentations will be recorded and made available at VideoLectures.net*

All accepted papers will be included in digitally published BMVC Workshop proceedings. As with the main BMVC conference topics include, but are not limited to:

* Statistics and machine learning for vision
* Stereo, calibration, geometric modelling and processing
* Person, face and gesture tracking
* Object and activity recognition
* Motion, flow and tracking
* Segmentation and feature extraction
* Model-based vision
* Image processing techniques and methods
* Texture, shape and colour
* Video analysis
* Document processing and recognition
* Vision for quality assurance, medical diagnosis, etc.
* Vision for visualization, interaction, and graphics

—-
Workshop chair: Teo deCampos

Program Committee

Mark Barnard – University of Surrey
Carl Henrik Ek – KTH Stockholm
Nazli FarajiDavar – University of Surrey
Ashish Gupta – University of Surrey
Piotr Koniusz – University of Surrey
Luca Marchesotti – Xerox Research Centre Europe
Julian McAuley – University of Stanford
Mukta Prasad – ETH Zurich
Jose Rodriguez-Serrano – Xerox Research Centre Europe
Violet Snell – University of Surrey
Eric Sommerlade – University of Oxford
Phil Tresadern – University of Manchester
Ruixuan Wang – University of Dundee
Fei Yan – University of Surrey
Huiyu Zhou – Queen’s University Belfast

—-
Workshop venue: University of Surrey, Guildford GU2 7XH, United Kingdom Contact email: bmvc2012@list.surrey.ac.uk Web page: http://bmvc2012.surrey.ac.uk/workshop.php
Please follow the link above for information about how to submit papers.

Registration of the workshop is FREE to all BMVC12 registered participants.

PhD vacancies at KU Leuven

Machine Understanding for interactive StorytElling

Description: The Department of Computer Science at KU Leuven has an open PhD position in the frame of the European MUSE (Machine Understanding for interactive StorytElling) project. MUSE will introduce a new way of exploring and understanding information by “bringing text to life” through 3D interactive storytelling. Taking as input natural language text like children’s stories or medical patient education materials, MUSE will process the natural language, translate it into formal knowledge that represents the actions, actors, plots and surrounding world, and then render these as virtual 3D worlds in which the user can explore the text through interaction, re-enactment and guided game play.

The PhD student will study advanced natural language processing techniques that enable the translation of natural language text to the necessary knowledge representation based on probabilistic models of translation, latent class paraphrasing models, and automatic methods for acquiring world knowledge from large corpora. He or she will focus on a specific aspect of natural language understanding and will work in a team of senior researchers in the frame of the MUSE project. The student will have contacts with outstanding European groups in the domains of machine reading of text, knowledge representation, cognitive understanding, and virtual storytelling.

The ideal candidate will recently have completed or will soon complete a master in computer science or a similar discipline. He or she has a large interest in natural language processing, statistical and probabilistic modeling, and machine learning. Excellent (honors-level) results in prior studies are required. The candidate is fluent in spoken and written English.
The interested candidate is asked to submit his or her CV and motivation letter to Marie-Francine Moens (Sien.Moens@cs.kuleuven.be) before June 21, 2012.

Latest application date: 2012-20-06.

Start date of the project: 2012-09-01.

Source of funding: EU FP7-296703 Future and Emerging Technologies call.

Duration of the project: 3 years +1 year extra funding available.

Mining of User Generated Content

The Department of Computer Science at KU Leuven has an open PhD position in the frame of cross-media processing of user generated content. User generated content, e.g. available through social networking sites on the Web, offers a wealth of information. The aim of the IWT-SBO project PARIS (Personalized AdveRtisements buIlt fom web Sources), by which the PhD is sponsored, is to study adequate natural language, image and video understanding techniques that mine user generated content. This is challenging as user generated content is often present in language that is not well-formed or in visual material that is not professionally captured. An important application of the PARIS technologies will be personalized advertising, where relevant advertisements are searched and generated that fit the world of living recognized in the user generated content. This requires efficient and scalable methods of “machine understanding” of content that can be applied in an online setting.

The offered PhD position regards the mining and linking of user generated content focusing on the joint processing of text and visual data (collaboration with a computer vision group). The focus is on developing information extraction methods that learn with a minimum of human supervision and that combine uncertain evidences from different sources making use of advanced probabilistic inference methods. An additional focus is to make the methods scalable and efficient for real-time use.

The ideal candidate will recently have completed or will soon complete a master in computer science or a similar discipline. He or she has a large interest in multimedia processing, statistical and probabilistic modeling, and machine learning. Excellent (honors-level) results in prior studies are required. The candidate is fluent in spoken and written English.
The interested candidate is asked to submit his or her CV and motivation letter to Marie-Francine Moens (Sien.Moens@cs.kuleuven.be) before June 21, 2012.

Key words: information retrieval, information extraction, data mining, machine learning, reasoning about uncertainty.


Latest application date: 2012-20-06.

Start date of the project: 2012-09-01.

Source of funding: IWT (SBO-110067).

Duration of the project: 4 years.

PhD Studentship in Statistical Machine Learning and Computational Systems Biology (Helsinki, Finland)

PhD studentship in developing novel probabilistic modelling and statistical inference methodology and applying these methods to problems in computational systems biology

Helsinki Institute for Information Technology HIIT, Department of Computer Science, University of Helsinki

—————————————————————

The Helsinki Institute for Information Technology (HIIT) and the Department of Computer Science at the University of Helsinki are looking for a skilled
DOCTORAL STUDENT.

The Department of Computer Science is the leading unit for computer science research and education in Finland. The focus areas of research and teaching at the department are (1) algorithms and machine learning, (2) networking and services, and (3) software systems. Three Finnish Academy-funded centres of excellence operate at the department, and it works in close collaboration with the Helsinki Institute of Information Technology. The department is one of ten national centres of excellence in university education. The department employs some 170 persons, and its total budget is 11 Million Euros. The department has an outstanding research infrastructure, including a 1920-core computing cluster

The doctoral student will develop novel probabilistic modelling and statistical inference methodology incorporating structured prior information from mechanistic models and apply these methods to problems in computational systems biology. The aim of the project is to develop hierarchical Gaussian process models for modelling gene expression and regulation in complex experiments, such as with evolutionarily related specimen. The work will take place in the group of Dr Antti Honkela but it will involve collaboration with experimental biologists. The project will build upon recent experience in application of Gaussian process models on modelling gene regulation by Dr Honkela and collaborators (Honkela et al., PNAS 2010; Titsias et al., BMC Systems Biology 2012).

A successful applicant must have a MSc degree in computer science, electrical engineering, mathematics, physics, or a related field. A strong mathematical background and an interest in Bayesian modelling and/or machine learning are necessary. An interest in computational biology is essential but no prior experience is necessary.

The application deadline is 21 June 2012.
For more details and application instructions, see
http://www.helsinki.fi/recruitment/index.html?id=56832

Harvest Project: Call for Participation

Under the auspices of the PASCAL Harvest Programme we will be running a twelve week project from 9th July to 28th September hosted by the Institute Jozef Stefan, Ljubljana, Slovenia. Ljubljana is situated close to the Julian Alps and a short distance from the Mediterranean.

The project La Vie (Learning Adapted Video Information Enhancer) involves machine learning to develop a recommender system for users of http://videolectures.net/.

La Vie will develop a proof-of-concept system that will provide users with advice on suitable videos for their needs. The key components that the project will bring to videolectures.net are:
1. topic extraction and modeling based on text extracted from associated slides and audio transcriptions. This will ensure that the devised user models can capture semantic level interests of the users.
2. inclusion of the information currently being logged about individual users in the recommender system running live on the videolectures site.
3. visualization of the developed recommender system. This will provide a topic landscape that will enable users to see the available videos emphasizing those likely to be of interest to the user.

Detailed description of the project is available at http://pascallin2.ecs.soton.ac.uk/PublicDocuments/LaVieProposal.pdf

The project was conceived by the following team: Rayid Ghani, Marko Grobelnik, Colin de la Higuera, Mitja Jermol, Alfons Juan, Matjaz Rihtar and John Shawe-Taylor and will be managed by Matjaz Rihtar.

The Harvest Project will cover the travel expenses, accommodation and subsistence for participants in the project not based at the Jozef Stefan Institute. We are looking to recruit programmers, machine learners, software engineers and welcome applicants at all levels.

We invite expressions of interest in participating in this project. Please indicate interest by replying to this email before 11th of June and include a short CV and the name of one referee.

Best regards,
Matjaz Rihtar & Mitja Jermol

Second Call for Papers: IEEE Transaction on Pattern Analysis and Machine Intelligence Special Issue on Bayesian Nonparametrics

Second Call for Papers
* Due Date for White Papers: June 30 *

IEEE Transaction on Pattern Analysis and Machine Intelligence Special Issue on Bayesian Nonparametrics

Topic description:
Bayesian nonparametric models are probabilistic models defined over infinite dimensional parameter spaces. Examples include Gaussian processes, used in regression and classification, where the parameter space consists of the set of smooth functions, and Dirichlet process mixture models for density estimation problems, where the parameter space is dense in the space of densities. Bayesian nonparametrics present a flexible framework for modeling complex data and a viable alternative to model selection, and have gained increasing attention in machine learning, statistics, and related fields in recent years.

We invite paper submissions for a special issue on Bayesian nonparametrics to be published in IEEE Transactions in Pattern Analysis and Machine Intelligence. Original research papers as well as overview and survey papers are welcome, on topics including, but not limited to:

• Statistical and learning theory for Bayesian nonparametric methods; • Novel Bayesian nonparametric models and stochastic processes; • Novel methodologies for learning and inference, including Monte Carlo, variational, message-passing, online, and large scale algorithms.
• Applications, to signal processing, image processing, speech, language processing and others.

Priority will be given to papers with high novelty and originality for research papers, and to papers with high potential impact for survey/overview papers.

Paper submission and review:
We invite interested authors to submit 2-page white papers outlining their submission by June 30, 2012, by email to
npbayes2012pami@gmail.com
Feedback on the white paper will be provided, and suitable submissions invited to submit full papers online, by August 31, 2012, through the TPAMI site at,
https://mc.manuscriptcentral.com/tpami-cs
selecting the choice that indicates this special issue. Peer reviewing will follow the standard IEEE review process. Full length manuscripts are expected at this second stage, following the TPAMI guidelines in http://www.computer.org/portal/web/peerreviewjournals/author

Time line:
Submission of 2-page white papers: June 30, 2012.
Feedback and invitations to submit full papers: July 15, 2012.
Submission of full papers: August 31, 2012.
First reviews: November 15, 2012.
Revisions due: January 15, 2013.
Decisions announced: February 28, 2013.
Final manuscripts due: March 31, 2013.

Guest editors:
• Ryan P. Adams, Harvard University, rpa@seas.harvard.edu • Emily Fox, University of Pennsylvania, ebfox@wharton.upenn.edu • Erik Sudderth, Brown University, sudderth@cs.brown.edu • Yee Whye Teh, University College London, ywteh@gatsby.ucl.ac.uk

Working with Watson: Postdoc positions available at TrentoRise (Italy)

Dear candidate,
have you been fascinated by the IBM Watson system’s achievements?
Have you ever thought that you could contribute to it?
If yes, there might be two great opportunities for this.

TWO Post-doctoral positions for 1 year (with the possibility of extension) are available
at the new IBM Language and Knowledge Center for Advanced Studies of TrentoRise – Italy
(TrentoRise is a joint research institution including the University of Trento, FBK and other important
research institutions of Trento)

Position 1: Information Extraction and Question Answering (Ref.Code IBM_PostDoc2012_IEQA)

This grant aims at developing a framework for Information Extraction and Retrieval based on deep
linguistic analysis. The main idea of the framework is to provide a flexible pipeline of NLP and IR
components, which can be used to model state-of-the-art systems, e.g., in the field of Question Answering.

Candidate Profile: the candidate must hold a PhD in Computer Science, e.g., Computational Linguistics,
Natural Language Processing, Information Retrieval or equivalent, and should be familiar with or
willing to learn the following topics:

– UIMA (Unstructured Information Management Architecture);
– Named Entity Recognition & Normalization / Concept Segmentation and Labeling
– Relation Extraction;
– Question interpretation, answer classification and extraction
– Dependency-based parsing, practice and theory
– Semantic role labeling
– Question analysis
– Search engine design
– Text Categorization/Filtering
– Document/passage ranking and re-ranking using different sources
– Indexing, search and retrieval for unstructured, semi-structured and structured data
– Retrieval models for Question Answering
– Relational models for sentence, paragraph and document representation

Programming skills are important whereas knowledge of the Italian language is not required.

Scientific tutors: Bernardo Magnini (FBK, Trento – http://hlt.fbk.eu/en/home)
Alessandro Moschitti (University of Trento – http://disi.unitn.it/moschitti/
– http://projects.disi.unitn.it/iKernels/)

Position 2: Machine Learning for NLP (Ref.Code IBM_PostDoc2012_LSM)

This grant aims at modeling and implementing a machine learning framework, which can be applied for
fast system prototyping. Kernel methods are seen as a viable approach to automatic feature engineering,
which is a severe bottleneck for the design of real-world applications. The other interesting problem that
will be studied concerns domain adaptation. Although the framework is supposed to be general, its
primary application domain will be natural language processing.

Candidate Profile: the candidate must hold a PhD in Computer Science, e.g., Machine Learning,
Computational Linguistics, Natural Language Processing, data mining or equivalent and should be
familiar with most of the following topics:

– Discriminative models, including Support Vector Machines and other Max-Margin approaches,
for tagging, extraction, (shallow) parsing and so on.
– Advanced data representation through Kernel Methods and Kernel Machines
– Online learning and Active Learning
– Supervised, Semi-Supervised, Unsupervised Learning, Domain Adaptation, Multi-task Learning in NLP
– Sequence labeling in NLP
– Relational Learning
– Graphical models, e.g., Conditional Random Fields and LDA, are a plus

Scientific tutor: Alessandro Moschitti (University of Trento – http://disi.unitn.it/moschitti/
– http://projects.disi.unitn.it/iKernels/)

Prof. Moschitti has been collaborating with the IBM Watson team since 2009. He has received two awards
from IBM. The postdocs (if successful in their research) will have the possibility to collaborate with
the IBM Watson team and carrying out working stage at IBM Watson of NY.

You can directly apply to

http://www.trentorise.eu/call-for-participation/bando-di-selezione-call-positions

If you want to know more, please send an email to
moschitti@disi.unitn.it
subject: IBM-POSTDOCS2012
salary net per month: 2k euros

The deadline for applications is June 30, 2012
(please note that the deadline indicated in the website above is going to be updated).

Your curriculum must show an appropriate record of publications in the areas of ML, NLP/CL or IR.

Best

Alessandro

CFP: BBCI Workshop 2012 on Advances in Neurotechnology September 17-19, Berlin, Germany

Call for Participation
Call for Poster Submissions

BBCI Workshop 2012 on Advances in Neurotechnology September 17-19, Berlin, Germany

Official: http://bbci12.ml.tu-berlin.de/

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

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

Submission Date: 2012-07-30
Notification of Acceptance: 2012-08-13
Workshop Date: 2012-09-17 – 2012-09-19

Organization
============

Bernstein Focus: Neurotechnology (BFNT-B) Humboldt University Berlin (HU) Berlin Institute of Technology (TUB) Charité – University Medicine Berlin Bernstein Center Computational Neuroscience Berlin (BCCN-B)

– Benjamin Blankertz (chair), Berlin Institute of Technology
– Ulrich Egert, University of Freiburg
– Siamac Fazli (poster co-chair), Berlin Institute of Technology
– Dario Farina, University of Göttingen
– Stefan Haufe (poster co-chair), Berlin Institute of Technology
– Klaus-Robert Müller (chair), Berlin Institute of Technology
– Susanne Schreiber (co-chair), Humboldt University Berlin
– Michael Tangermann (poster chair), Berlin Institute of Technology
– Jochen Triesch, University of Frankfurt

Matthias L. Jugel, BFNT-B/Industry
Imke Weitkamp, BFNT-B/Coordination

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

Different approaches to Brain-Computer Interfaces have been developed, each one with specific solutions that range from understanding and explaining cognitive functions over communicating with real and virtual environments by thought alone to real-time monitoring of cognitive states.

The Advances in Neurotechnology Workshop presents an overview, in-depth tutorials and discussions on the latest research at all levels of Neurotechnology and BCI research. What is presented will cover invasive recording, semi-invasive ECoG, non-invasive EEG, non-invasive NIRS and fMRI measurement and potential combinations of the different methods. Additional focus will be devoted to advances in data analysis.

The poster session following the tutorials will cross over into the BBCI barbecue, smoothing discussions with drinks and food.

Following the workshop there will be a summerschool on selected topics in BCI and neurotechnology from September 20th to 28th.
It has educational tutorials in the morning session (two tutorials of 2h each, held by internationally renowned researchers), and practical hand-ons sessions in the afternoon. The practical sessions are partly multi-track and will allow researchers in BCI/neurotechnology to complement their expertise in the interdisciplinary field.

Submission
==========

Please send your posters (in PDF) or abstracts (max. 2 pages, PDF or plain text) to the poster chair Michael Tangermann , no later than 2012-07-30.

Poster size should be a maximum of A0 (width x height: 841mm × 1189mm)

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

– Felix Biessmann, Berlin Institute of Technology
– Benjamin Blankertz, Berlin Institute of Technology
– Mark Cohen, UCLA
– Tom Eichele, Haukeland University Hospital, Bergen, Norway
– Dario Farina, BFNT Göttingen
– Rainer Goebel, University Maastricht
– John-Dylan Haynes, Bernstein Center for Computational Neuroscience
– Bo Hong, Tsinghua University, Beijing, China
– Yukiyasu Kamitani, ATR Computational Neuroscience Laboratories, Kyoto
– Motoaki Kawanabe, ATR Computational Neuroscience Laboratories, Kyoto
– Christof Koch, California Institute of Technology
– Andrea Kübler, Universität Würzburg
– Seong-Whan Lee, Dept. of Brain and Cognitive Engineering, Korea
– Donatella Mattia, Fondazione Santa Lucia, IRCCS, Italy
– José del R. Millán, Ecole Polytechnique Fédérale de Lausanne (EPFL)
– Klaus-Robert Müller, Berlin Institute of Technology
– Gernot Müller-Putz, TU Graz
– Gerwin Schalk, Wadsworth Center

Venue
=====

Audimax der Humboldt-Universität zu Berlin, Unter den Linden 6 / Dorotheenstr. 17-19, Berlin, Germany

Workshop Fees
=============

Business: 300 EUR
Standard: 250 EUR

* Early Registration Discount (until 2012-08-19)

Academic : 200 EUR
Bernstein: 100 EUR
Students : 50 EUR

Funding
=======

The workshop is supported by the Bernstein Focus: Neurotechnology Berlin.

ECML PKDD 2012 Discovery Challenge on Large Scale Hierarchical Text Classification

ECML/PKDD 2012 Discovery Challenge: Third Challenge on Large Scale Hierarchical Text Classification

Web site: http://lshtc.iit.demokritos.gr/
Email: lshtc_info@iit.demokritos.gr

This year’s discovery challenge hosts the third edition of the successful PASCAL challenges on large scale hierarchical text classification. The challenge comprises three tracks and it is based on two large datasets created from the ODP web directory (DMOZ) and Wikipedia. The datasets are multi-class, multi-label and hierarchical. The number of categories ranges between 13,000 and 325,000 roughly and the number of documents between 380,000 and 2,400,000.

The tracks of the challenge are organized as follows:

1. Standard large-scale hierarchical classification
a) On collection of medium size from Wikipedia
b) On a large collection from Wikipedia
2. Multi-task learning, based on both DMOZ and Wikipedia category systems
3. Refinement-learning
a) Semi-Supervised approach
b) Unsupervised approach

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

*** Please note that participants can now upload intermediary results on the web site and track the progress of their work!

Important dates:

– March 30, start of the challenge
– April 20, opening of the evaluation
– June 29, closing of evaluation
– July 20, paper submission deadline
– August 3, paper notifications

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