Vision and Sports Summer School 2010

Call for Participation

VISION AND SPORTS SUMMER SCHOOL

Zurich, 16-20 August 2010

http://www.vision.ee.ethz.ch/summerschool2010/

email: vs3 (at) vision.ee.ethz.ch

application deadline: 10 May 2010

OVERVIEW

Vision and Sports is a special special kind of summer school. In addition to a broad-range of lectures on state-of-the-art Computer Vision techniques, it offers exciting sport activities, such as Ultimate Frisbee, Volleyball, and Table Tennis. Sports are organized by the same internationally renowned experts who deliver the lectures. The school offers the best of both worlds to participants: high-quality teaching on Computer Vision, and lots of fun with a variety of attractive sports. This offers plenty of opportunity for personal contact between students and teachers.

The Vision and Sports Summer School covers a broad range of subjects, reflecting the diversity of Computer Vision. Each lecture will cover both basic aspects and state-of-the-art research. Every day there are two Computer Vision classes and one sports session. The classes include both lectures and practical exercises.

The school is open to about 50 participants, and is targeted mainly to young researchers (Master students and PhD students in particular).

CONFIRMED TEACHERS (MORE WILL FOLLOW)

Daniel Cremers
TU Muenchen

Christoph Lampert
MPI Tuebingen

Vittorio Ferrari
ETH Zurich

Jiri Matas
Czech Technical University
Tennis

Ondrej Chum
Czech Technical University

Carsten Rother
Microsoft Cambridge

Pushmeet Kohli
Microsoft Cambridge

COMPUTER VISION LECTURES

Topics will include:

Local feature extraction
Multi-view geometry
3D reconstruction
Large-scale specific object recognition
Appearance-based object categorization
Shape representation and matching
Contour-based object categorization
Kernel Methods for Computer Vision
Markov Random Fields and Conditional Random Fields for Computer Vision
Continuous optimization for Computer Vision

SPORT ACTIVITIES

Tennis, Volleyball, Ultimate Frisbee, Unihockey, Table Tennis, Basketball

APPLICATION

The school is open to about 50 participants. Please apply online at

http://www.vision.ee.ethz.ch/summerschool2010/

Although priority will be given to young researchers (Master/PhD students in particular), applications from senior researchers and industrial professionals are welcome as well. The registration fee is expected to be around 400 Euro. This fee includes all classes, sports activities, coffee breaks, lunches, and a social dinner. For hotel accommodation, students will get discount rates on hotels affiliated with the school.

Applicants should apply before 10 May 2010.
Notification of acceptance will be sent by 31 May 2010.

MORE INFORMATION

http://www.vision.ee.ethz.ch/summerschool2010/

PhD position in Statistical Natural Language Processing

A PhD studentship is available in Statistical Natural Language Processing at the University of Sheffield. Details are given below. For further information please contact Trevor Cohn (tcohn@dcs.shef.ac.uk).

Starting: around October 2010
Length: three years
Stipend: £13,290 pa (UK nationals) or approx. £8,000 (EU nationals)
Closing date for applications is 16th April 2010.

The aim of this studentship is to design machine learning methods to better understand and utilise natural language texts. Natural language processing (NLP) now provides many indispensable tools for working with large unstructured text collections, allowing effective search, information extraction and translation. Language poses a number of difficult and interesting machine learning challenges. Statistical models can provide insight into the nature of language while also providing practical tools. Possible topics include grammar induction, parsing, language modelling, topic modelling and machine translation.

Candidates should have a strong background in Computer Science or Mathematics. Experience with machine learning and probabilistic modelling techniques is essential, and experience in graphical models and Bayesian inference would be highly desirable. A knowledge of linguistics and/or fluency in multiple languages would also be desirable, but is not strictly necessary.

For further details please visit
http://www.dcs.shef.ac.uk/~tcohn/studentship.html
or email Dr Trevor Cohn (tcohn (at) dcs.shef.ac.uk)

MCS – 9th International Workshop on Multiple Classifier Systems – Cairo, April 7-9 2010

MCS 2010 – 9th International Workshop on Multiple Classifier Systems
Nile University, Cairo, Egypt, April 7-9 2010
http://www.diee.unica.it/mcs/

MCS 2010 is the ninth workshop in a well-established series
of meetings providing an international forum for the
discussion of issues in multiple classifier system design.
The aim of the workshop is to bring together researchers from
diverse communities concerned with this topic, including
neural network, pattern recognition, machine learning and
statistics. Information on the previous MCS workshops can
be found on www.diee.unica.it/mcs . The special focus of
MCS 2010 will be on the application of multiple classifier
systems in data mining, medical imaging and bioinformatics.

* WORKSHOP CHAIRS *
– Neamat El Gayar (Nile Univ., Egypt)
– Josef Kittler (Univ. of Surrey, United Kingdom)
– Fabio Roli (Univ. of Cagliari, Italy)

Sponsored by the PASCAL2 Network of Excellence

Endorsed by the IAPR

***********************
* PRELIMINARY PROGRAM *
***********************

————————
Day 1: WEDNESDAY 7 APRIL
————————
Pick up (8:15 am Hilton 6th October, 8:30 am NOVOTEL 6th October)

9:00 – 09:20
Registration

09:20 -09:30
Opening
Neamat El Gayar, Josef Kittler and Fabio Roli

———————
Classifier Ensemble I
Session Chair: Ludmila Kuncheva

09:30
Weighted Bagging for Graph based One-Class Classifiers
Santi Segui, Laura Igual and Jordi Vitria

09:55
Improving multilabel classi_cation performance by using Ensemble of Multi-label Classi_ers
Muhammad Atif Tahir, Josef Kittler, Krystian Mikolajczyk, and Fei Yan

10:20
New Feature Splitting criteria for Co-training using Genetic Algorithm Optimization
Ahmed Salaheldin and Neamat El Gayar

10:45
Incremental Learning of New Classes in Unbalanced Datasets: Learn++.UDNC
Gregory Ditzler, Michael D. Muhlbaier and Robi Polikar

————
11:10
Coffee Break

————–
Invited Talk I
Session Chair: Fabio Roli

11:30
Gavin Brown
Some Thoughts at the Interface of Ensemble Methods and Feature Selection

———————-
Classifier Ensemble II
Session Chair: Josef Kittler

12:15
Tomographic Considerations in Ensemble Bias/Variance Decomposition
David Windridge

12:40
Choosing Parameters for Random Subspace Ensembles for fMRI Classification
Ludmila I. Kuncheva and Catrin O. Plumpton

13:05
An Experimental Study on Ensembles of Functional Trees
Juan J. Rodr__guez, C_esar Garc__a-Osorio, Jes_us Maudes, and Jos_e Francisco D__ez-Pastor

——————–
13:25
Lunch/ Poster Set Up

———————————–
Session I (Classifier Ensemble III)
Session Chair: David Windridge

14:45
Multiple classi_er systems under attack
Battista Biggio, Giorgio Fumera, and Fabio Roli

15:10
SOCIAL: Self-Organizing ClassIfier ensemble for Adversarial Learning
Francesco Gargiulo and Carlo Sansone

15:35
Unsupervised Change-Detection in Retinal Images by a Multiple Classifier Approach
Giulia Troglio, Marina Alberti, J_on Atli Benediksson, Gabriele Moser, Sebastiano Bruno Serpico and Einar Stef_ansson

———————–
Poster session & Coffee
16:00

Forecast Combination Strategies for Handling Structural Breaks for Time Series Forecasting
Waleed M. Azmy, Amir F. Atiya, Hisham El-Shishiny

A Multiple Classi_er System for Classi_cation of LIDAR Remote Sensing Data Using Multi-class SVM
Farhad Samadzadegan, Behnaz Bigdeli, Pouria Ramzi

A Multi-Classi_er System for O_-Line Signature Veri_cation Based on Dissimilarity Representation
Luana Batista, Eric Granger and Robert Sabourin

A Multi-Objective Sequential Ensemble for Cluster Structure Analysis and Visualization Application to Gene Expression
Noha A. Yousri

Combining 2D and 3D Features to Classify Protein Mutants in HeLa Cells 282
Carlo Sansone, Vincenzo Paduano, and Michele Ceccarelli

An experimental comparison of Hierarchical Bayes and True Path Rule ensembles for protein function prediction.
Matteo Re and Giorgio Valentini

Recognizing Combinations of Facial Action Units with Di_erent Intensity Using a Mixture of Hidden Markov Models and Neural Network
Mahmoud Khademi, Mohammad Taghi Manzuri-Shalmani,, Mohammad Hadi Kiapour, and Ali Akbar Kiaei

———————————–
End of scientific program for Day 1
17:30

18:00
Welcome Reception at the new Campus for Nile University

19:30
Return to hotels (Novotel 6th October, Hilton 6th October)
End of Day 1

————————
Day 2: THURSDAY 8 APRIL
————————
Pick up (8:15 am Hilton 6th October, 8:30 am NOVOTEL 6th October,)

——————–
Classifier Diversity
Session Chair: Gunther Palm

9:20
“Good” and “Bad” Diversity in Majority Vote Ensembles
Gavin Brown and Ludmila I. Kuncheva

9:45
Multi-Information Ensemble Diversity
Zhi-Hua Zhou and Nan Li

————-
Invited Paper
Session Chair: Horst Bunke

10:10
Multiple classifer systems for the recognition of human emotions
Friedhelm Schwenker, Stefan Scherer, Miriam Schmidt, Martin Schels, Michael Glodek

——
10:55
Coffee

————————–
Boosting and bootstrapping
Session Chair: Robert Duin

11:30
Class-Separability Weighting and Bootstrapping in Error Correcting Output Code Ensembles
R.S.Smith and T.Windeatt

11.55
Boosted Geometry-based Ensembles
Oriol Pujol

12.20
Online Non-Stationary Boosting
Adam Pocock, Paraskevas Yiapanis, Jeremy Singer, Mikel Luj_an, and Gavin Brown

————————–
Combining multiple kernels
Session Chair: Giorgio Fumera

12:45
A Support Kernel Machine for Supervised Selective Combining of Diverse Pattern-Recognition Modalities
Alexander Tatarchuk, Eugene Urlov, Vadim Mottl, David Windridge

13:10
Combining Multiple Kernels by Augmenting the Kernel Matrix
Fei Yan Krystian Mikolajczyk Josef Kittler Muhammad Atif Tahir

—–
13.25
Lunch

———————–
Handwriting recognition
Session Chair: Zhi-Zhou

14:45
Combining Neural Networks to Improve Performance of Handwritten Keyword Spotting
Volkmar Frinken, Andreas Fischer and Horst Bunke

15:10
Combining Committee-based Semi-supervised and Active Learning and Its Application to Handwritten Digits Recognition
Mohamed Farouk Abdel Hady, Friedhelm Schwenker

15:35
Using Diversity in Classi_er Set Selection for Arabic Handwritten Recognition
Nabiha Azizi, Nadir Farah, Mokhtar Sellami, Abdel Ennaji

16:00
End of scientific program for Day2

—————————————————
Transportation to City and Banquet at El Azhar Park

Return to hotels (Novotel 6th October, Hilton 6th October)

End of Day 2

———————
Day 3: FRIDAY 9 APRIL
———————
Pick up (8:15 am Hilton 6th October, 8:30 am NOVOTEL 6th October,)

——————————————-
Session I (Classifier Ensemble / Selection)
Session Chair: Terry Windeatt

09:30
Dynamic Selection of Ensembles of Classi_ers Using Contextual
Information
Paulo R. Cavalin, Robert Sabourin, and Ching Y. Suen

09:55
Selecting Structural Base Classi_ers for Graph-based Multiple Classi_er
Systems
Wan-Jui Lee, Robert P.W. Duin and Horst Bunke

10:20
A double pruning algorithm for classi_cation ensembles
V__ctor Soto, Gonzalo Mart__nez-Mu~noz, Daniel Hern_andez-Lobato, and Alberto Su_arez

10:45
Estimation of the number of clusters using multiple clustering validity indices
Krzysztof Kryszczuk and Paul Hurley

————-
11:10
Coffee Break

—————–
Panel Discussion
Moderator: Fabio Roli , Mohamed Kamel, Ludmila Kuncheva , Robi Polikar
11:30 – 13.00

—–
13:00
Lunch

End of scientific program for Day 3

Optional Half Day Cultural Program (Pyramids visit and Sound and Light show)

Return to hotels (Novotel 6th October, Hilton 6th October)

End of Day 3

Call for registration – Summer School on Statistical Inference in Computational Biology

SICSA International Summer School on

Statistical Inference in Computational Biology

National E-Science Centre, Edinburgh, United Kingdom

14-18 June 2010

http://www.dcs.gla.ac.uk/inference/sicb/

CONFIRMED SPEAKERS
—————-
Terry Speed (University of California, Berkeley)
Michael Stumpf (Imperial College)
Dirk Husmeier (Biomathematics and Statistics Scotland)
Chris Holmes (University of Oxford)
Magnus Rattray (University of Manchester)
Manfred Opper (Technical University of Berlin)

SCOPE
—–

Technological advances in the life sciences are producing vast amounts of data describing organisms at all levels of organisation. The impact of this on Informatics and the Computational Sciences has been enormous: the new disciplines of computational biology and bioinformatics were born to organise and model these data, and are now some of the fastest growing and most exciting areas in computer science. The increasing awareness of the noisy and incomplete nature of most biological data has led to a widespread use of statistical and machine learning tools within the field.

The school will focus on the role of statistical inference in biological modelling, with a particular emphasis on the Bayesian framework. It is mostly aimed at PhD students in computational subjects or quantitative biology, although early career researchers wishing to acquire more statistical modelling skills are also welcome. The school will consist of 6 4-hour modules, each delivered by an expert of international standing over 5 days. The first two sessions will serve as an introduction to multi-variate and Bayesian statistics respectively with a leaning towards the tools required in Computational Biology. The remaining sessions will cover four of the main inference tasks in Computational Biology – network reconstruction, inference within models of biological processes, inference in phylogenetics and phenotype-genotype associations to explain genetic diseases.

REGISTRATION AND ACCOMMODATION
——————————

Registration is now open! Numbers are limited – please register as soon as possible to guarantee your place.

Registration for the school will cost £250. Please register online at http://www.nesc.ac.uk/esi/events/1062/.

The venue (NESC) also have details on local accommodation. Please see http://www.nesc.ac.uk/esi/events/1062/ for more details.

SICSA students: SICSA will pay for both registration and accommodation for PhD students in Scottish Informatics and Computing Science departments that belong to the SICSA network. Please contact the organisers (sicb@dcs.gla.ac.uk) for more details.

Members of the PASCAL NoE: We are able to offer free registration to a small number of PASCAL affiliated PhD students. Please contact the organisers (sicb@dcs.gla.ac.uk) for more information.

Internship in the area of Reinforcement Learning at INRIA Lille – Team SequeL, France

Applicants are invited for an up to 6 months internship at INRIA Lille – Team Sequel working with Remi Munos and Mohammad Ghavamzadeh.

This is a joint project with Shie Mannor at Technion in Haifa, Israel, and is funded by PASCAL2 European Network of Excellence. The project is carried out at INRIA Lille within the SequeL team with the opportunity to visit Shie Mannor’s team at Technion.

The goal of this project is to devise, analyze, implement, and experiment with alternative approaches to reinforcement learning when
the dimension of the input space is large and possibly infinite. We would like to investigate the possibility of using the recent results
in sparse representations using L1-regularization and random projections in reinforcement learning.

Candidates must have either a Masters degree or be in the last stage of their Masters program in machine learning, statistics, or related
fields, with ideally some background in reinforcement learning, kernel methods, sparse methods, and optimization.

After the internship, there would be a possibility for the student to pursue a Ph.D. program at INRIA Lille – Team SequeL.

Candidates should send a detailed CV to Remi Munos (remi.munos at inria.fr) and Mohammad Ghavamzadeh (mohammad.ghavamzadeh at inria.fr).

Faculty position in statistical learning at the Department of Computer Science at the University of Lille III, France

The Department of Mathematics, Economics, and Computer Science at the University of Lille III invites applications for a tenure-track faculty position in statistical learning. The position is associated with the French National Institute for Research in Computer Science and Control (INRIA). Thus the recruit will also join one of the two following research groups at INRIA Lille:

– mostrare: http://mostrare.lille.inria.fr
– sequel: http://sequel.lille.inria.fr

The position requires a Ph.D. in Computer Science or a closely related fields at the time of employment. Candidates must show outstanding research, teaching, and graduate student mentorship potential. More information about the position is available at https://sequel.lille.inria.fr/SequeL/ChaireL32010

The department is constituted of approx 30 permanent members, mostly computer scientists (10), mathematicians, and economists. This position is mostly aiming at teaching in master degrees, classes on data mining, knowledge extraction from databases, machine learning, and XML technologies. Based on sound concepts, practical issues are expected to receive a great deal of attention.

APPLICATION INSTRUCTIONS

Full consideration will be given to applications received by March 25, 2010. All the information on how to apply is available at https://sequel.lille.inria.fr/SequeL/ChaireL32010

UAI 2010 Second Call for Papers

The 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010)

July 8th – July 11th, 2010, Catalina Island, California, U.S.A. (near Los Angeles)

http://event.cwi.nl/uai2010

SECOND CALL FOR PAPERS (DEADLINE MARCH 12TH)

IMPORTANT NOTICE – NEW FEATURE
UAI has traditionally mostly attracted submissions from computer scientists, even though reasoning under uncertainty is an important topic in many other areas such as, for example, statistics, economics (game theory), information theory and philosophy. This year, we especially encourage submissions from researchers working in such fields.

To accommodate the publishing traditions of these fields, authors may instead submit working papers that are under review or nearly ready for journal review. These submissions will be subject to review and considered for presentation at the conference but not for publication in the proceedings. These submissions need not conform to the conference paper format. Abstracts (max. 1 page) of accepted working papers will be included in the proceedings and must be coupled with a URL that points to the full paper and that will be reliable for at least two years. Open access is strongly preferred although the paper can be hosted by a publisher who takes copyright and limits access, as long as there is a link to the location.

GENERAL INFO
The 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010) will take place on July 8-11, 2010 on beautiful Catalina Island, California (near Los Angeles). The tutorial day is on July 8th, and the main conference is from July 9 to 11. We have an exciting program of tutorials and invited speakers, see below.

We encourage submissions that report on theoretical or methodological advances in modeling, inference, learning and decision making under uncertainty. Submissions reporting on novel and insightful applications of these techniques within intelligent systems are also strongly encouraged. Examples of such application areas include, but are not limited to, computational biology, computer vision, speech processing, computational linguistics, information retrieval, medical systems, multi-agent systems and sensor networks.

IMPORTANT DATES
• Friday, March 12, 2010 UAI paper submissions due (11.59pm, GMT)
• Monday, March 22, 2010 UAI student paper certification (11.59pm, GMT)
• Monday, April 26, 2010 Reviews available/author feedback period begins
• Wednesday, May 5, 2010 Author feedback on reviews due (11.59pm, GMT)
• Monday, May 31, 2010 UAI author notification
• Monday June 14, 2010 UAI camera ready copy of accepted papers due (11.59pm, GMT)
• Monday June 21, 2010 Scholarship applications due
• Thursday June 24, 2010 Early registration deadline
• July 8, 2010 Tutorials
• July 9-11, 2010 UAI conference
NOTE: midnight GMT = 7pm EST = 4pm PST

PAPER SUBMISSION DETAILS
UAI 2010 requires electronic submission of papers and abstracts according to instructions that will be posted before February 26th at event.cwi.nl/uai2010.
A submitted paper should not be under review by any other conference or scientific journal at the time it is submitted to UAI 2010 or at any time during the reviewing period of UAI 2010. At the time of submission, a paper should also not have already been accepted for publication in a journal. We do coordinate with several other conferences to avoid that essentially identical papers are sent to UAI and any of these other conferences.

PRESENTATION, PROCEEDINGS, and AWARDS
Accepted papers will be presented at the conference in either plenary or poster sessions. At least one of the paper’s authors should be present at the conference to present the work. All accepted papers will be included in the Proceedings of the Twenty Sixth Conference on Uncertainty in Artificial Intelligence. The program committee will select papers for special distinction in two categories at UAI 2010: a “Best Paper” award, and an “Outstanding Student Paper” award. The conference home page will contain instructions for certifying student status with regards to the latter award.

ORGANIZATION
General Conference Chair
Jeff Bilmes, University of Washington

Program Co-Chairs
Peter Grünwald, Centrum voor Wiskunde en Informatica and Leiden University
Peter Spirtes, Carnegie Mellon University

TUTORIALS (PRELIMINARY TITLES)

Learning and Reasoning With Incomplete Data: Foundations and Algorithms
Manfred Jaeger, Aalborg University

Non-Gaussian methods for learning linear structural equation models
Shohei Shimizu and Yoshinobu Kawahara, Osaka University