CFP: Data Mining School in Maastricht, The Netherlands: October 22 – October 24, 2012

*********************************************************************
** **
** 10th SCHOOL ON DATA MINING, Maastricht University, **
** Maastricht, The Netherlands **
** http://www.unimaas.nl/datamining/ **
** **
** Apologies if you receive multiple copies of this announcement **
** Please forward to anyone who might be interested **
** **
*********************************************************************

School on Data Mining

An intensive 3-day introduction to methods and applications

Department of Knowledge Engineering, Maastricht University,
Maastricht, The Netherlands
October 22 – October 24, 2012

Introduction
Most business organizations collect terabytes of data about business
processes and resources. Usually these data provide just “facts and
figures”, not knowledge that can be used to understand and eventually
re-engineer business processes and resources. Scientific community in
academia and business have addressed this problem in the last 20 years
by developing a new applied field of study known as data mining.
In practice data mining is a process of extracting implicit,
previously unknown, and potentially useful knowledge from data. It
employs techniques from statistics, artificial intelligence, and
computer science. Data mining has been successfully applied for
acquiring new knowledge in many domains (like Business, Medicine,
Biology, Economics, Military, etc.). As a result most business
organizations need urgently data-mining specialists, and this is
the point where this school comes to help.

Description
Our school on data mining tries to find a balance between theory and practice.
Each lecture is accompanied by a lab in which participants experiment
with the techniques introduced in the lecture. The lab tool is Weka, one
of the most advanced data-mining environments. A number of real data
sets will be analysed and discussed. In the end of the school
participants develop their own ability to apply data-mining techniques
for business and research purposes.

Content
The school will cover the topics listed below.
– The Knowledge Discovery Process
– Data Preparation
– Basic Techniques for Data Mining:
+ Decision-Tree Induction
+ Rule Induction
+ Instance-Based Learning
+ Bayesian Learning
+ Support Vector Machines
+ Regression Techniques
+ Clustering Techniques
+ Association Rules
– Tools for Data Mining
– How to Interpret and Evaluate Data-Mining Results

Intended Audience
This school is intended for four groups of data-mining beginners:
students, scientists, engineers, and experts in specific fields who need
to apply data-mining techniques to their scientific research, business
management, or other related applications.

Prerequisites
The school does not require any background in databases, statistics,
artificial intelligence, or machine learning. A general background in
science is sufficient as is a high degree of enthusiasm for new
scientific approaches.

Certificate
Upon request a certificate of full participation will be provided after
the school.

Registration
To register for the school please send an email to:

smirnov@maastrichtuniversity.nl

In the e-mail please specify:
– Name
– University / Organisation
– Address
– Phone
– E-Mail

Registration Deadline: October 15, 2012

Registration fees
Academic fee 600 Euros
Non-academic fee 850 Euros

Coffee breaks are included in the price. The local
cafeteria will be available for lunch (not included).

Registartion e-mail: smirnov@maastrichtuniversity.nl

Regular mail should be sent to:

Evgueni Smirnov
Department of Knowledge Engineering
Faculty of Humanities and Sciences
Maastricht University
P.O.Box 616
6200 MD Maastricht
The Netherlands
Phone: +31 (0) 43 38 82023
Fax: +31 (0) 43 38 84897
E-mail: smirnov@maastrichtuniversity.nl

*** ECML PKDD 2012 *** CALL FOR PARTICIPATION *** MID REGISTRATION DEADLINE: AUGUST 31 ***

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) will take place in Bristol, UK from September 24th to 28th, 2012.

ECML-PKDD is the prime European scientific event in machine learning and data mining. It will feature presentations of contributed papers and invited speakers, a wide program of workshops and tutorials on the first and last days, a discovery challenge, and a DINe track with demo, industry, and ‘nectar’ talks.

Keynote talks

Schedule

Workshops

Tutorials

The mid registration deadline with reduced registration fee is August 31st, 2012.

Accommodation is booked directly with the hotels: reduced rates are available on a first-come-first-serve basis and some block bookings will be released soon, so please act now to avoid disappointment!

Registration

Hotels

We look forward to welcoming you in Bristol this September.

Peter Flach, Tijl De Bie and Nello Cristianini, University of Bristol
ECML-PKDD 2012 General and Programme Chairs
ECMLPKDD2012@cs.bris.ac.uk

IDA 2012: Final Call for Graduate Student Research Poster Session

Announcing the
GRADUATE STUDENT RESEARCH SPOTLIGHT SESSION
at the
INTERNATIONAL SYMPOSIUM ON INTELLIGENT DATA ANALYSIS 2012
25-27 October 2012
Helsinki, Finland

The IDA Symposium is promoting a poster track for graduate-student
research. This session will be open to the public and to the local
research community. It will be a great opportunity to present your
work to a broad audience and it takes only a greatly reduced
registration rate for participants.

If you are a graduate student and would like to present and discuss
your research at this session, submit a one-page pdf abstract by email
to ida2012-posters@cis.hut.fi by 1 September 2012.

To attract the audience to your poster, you are also welcome to submit
a video of two minutes length. The best video presentation will be
awarded a prize of 300 EUR. Details at http://ida2012.org/phd.html

The IDA-2012 organizing team

General Chair Program Chairs Poster Chair
Jaakko Hollmen Frank Klawonn & Allan Tucker Frank Hoppner

Machine Vision and Applications: Special issue on Benchmark Evaluation of RGB-D based Visual Recognition Algorithms

Visual recognition is a critical component of machine intelligence. For a robot to behave autonomously, it must have the ability to recognize its surroundings (I am in the office; I am in the kitchen; On my right is a refrigerator). Natural human computer interaction requires the computer to have the ability to recognize human’s gestures, body languages, and intentions. Recently, the availability of cheap 3D sensors such as Microsoft Kinect has made it possible to easily capture depth maps in real time, and therefore use them for various visual recognition tasks including indoor place recognition, object recognition, and human gesture and action recognition. This in turn poses interesting technical questions such as:

1. What are the most discriminative visual features from 3D depth maps?
Even though one could treat depth maps as gray images, depth maps consist of strong 3D shape information. How to encode the 3D shape information is an important issue for any visual recognition tasks.

2. How to combine depth maps and RGB images? An RGB-D sensor such as Microsoft Kinect provides a depth channel as well as a color channel.
The depth map contains shape information while the color channel contains texture information. The two channels complement each other, and how to combine them in an effective way is an interesting problem.

3. What are the most suitable paradigms for recognition with RGB-D data?
With depth maps, foreground background separations are easier, and in general, better object segmentations can be obtained than with conventional RGB images. Therefore the conventional bag of feature approaches may not be the most effective approaches. New recognition paradigms that leverage depth information are worth exploring.

Scope

This special issue covers all aspects of RGB-D based visual recognition.
It emphasizes on the evaluation on two benchmark tasks: ImageCLEF Robotic Vision Challenge (http://www.imageclef.org/2012/robot) and CHALEARN Gesture Challenge (http://gesture.chalearn.org/). The special issue is also open to researchers that did not submit runs to either of the two challenges, provided they will test their methods on at least one of the two datasets. In addition to the two benchmark tasks, researchers are welcome to report experiments on other datasets to further validate their techniques.
Topics include but are not limited to:

new machine learning techniques that are successfully applied to either of the two benchmark tasks o novel visual representations that leverage the depth data o novel recognition paradigms o techniques that effectively combine RGB features and depth features o analysis of the results of the evaluation on either of the two benchmark tasks theoretical and/or practical insights into the problems for the semantic spatial modeling task, and/or for the robot kidnapping task in ImageCLEF Robotic Vision Challenge o theoretical and/or practical insights into the one-shot recognition problem in the CHALEARN Gesture Challenge o computational constraints of methods in realistic settings o new metrics for performance evaluations

Information for Authors:

Authors should prepare their manuscripts according to the author guideline from the online submission page of Machine Vision and Applications (http://www.editorialmanager.com/mvap/).

Important Dates (tentative):

o Manuscript submission deadline: January 30, 2013 o First round review decision: May, 2013 o Second round review decision: September, 2013 o Final manuscript due: November, 2013 o Expected publication date: January, 2014

Guest Editors:

o Barbara Caputo, Idiap Research Institute, Switzerland o Markus Vincze, The Institute of Automation and Control Engineering, Austria o Vittorio Murino, Istituto Italiano di Tecnologia, Italy o Zicheng Liu, Microsoft Research, United States

Two PhD positions in Computer Vision at the University of Edinburgh

University of Edinburgh
School of Informatics
Two PhD positions in Computer Vision

Applications are invited for two PhD students to work in the School of Informatics on a project funded by a European Research Council Starting Grant. The project is on lifelong visual learning: its main goal is to develop methods to progressively learn new visual concepts helped by the knowledge of concepts learned before. A second, related topic of interest is learning visual object categories from consumer videos.

Applicants must have:

* Master degree in Computer Science or Mathematics
* Excellent programming skills (the project is in Matlab and C++)
* Solid mathematics foundations (especially algebra and statistics)
* Highly motivated
* Fluent in English, both written and spoken
* UK or EU nationality is mandatory – applicants of other nationalities will not be considered
* Experience in computer vision and/or machine learning is a plus

The School of Informatics at Edinburgh is one of the top-ranked departments of Computer Science in Europe and offers an exciting research environment. Edinburgh is a beautiful historic city with a high quality of life.

Starting date: January 2013 or later

The PhD work will be carried out under the supervision of Dr. Vittorio Ferrari. For an overview of current research activities, please visit

http://groups.inf.ed.ac.uk/calvin/

For pre-screening, please send applications to the email address below, including:
* complete CV
* title and abstract of master thesis
* complete grades for all exams passed during both the bachelor and master
(to obtain this position you need high grades, especially in mathematics and programming disciplines)
* the name and email address of one reference (preferably your master thesis supervisor)
* if you already have research experience, please include a publication list

email: vferrari@staffmail.ed.ac.uk

NIPS workshop: BigVision 2012

Big Data Meets Computer Vision: First International Workshop on Large Scale Visual Recognition and Retrieval (BigVision 2012)

Held in conjunction with NIPS 2012. December 7 or December 8 (TBD), 2012. Lake Tahoe, Nevada, USA.

https://sites.google.com/site/bigvision2012/

=============
Overview
=============

The emergence of “big data” has brought about a paradigm shift throughout computer science. Computer vision is no exception. The explosion of images and videos on the Internet and the availability of large amounts of annotated data have created unprecedented opportunities and fundamental challenges on scaling up computer vision.

Over the past few years, machine learning on big data has become a thriving field with a plethora of theories and tools developed.
Meanwhile, large scale vision has also attracted increasing attention in the computer vision community. This workshop aims to bring closer researchers in large scale machine learning and large scale vision to foster cross-talk between the two fields. The goal is to encourage machine learning researchers to work on large scale vision problems, to inform computer vision researchers about new developments on large scale learning, and to identify unique challenges and opportunities.

This workshop will focus on two distinct yet closely related vision
problems: recognition and retrieval. Both are inherently large scale.
In particular, both must handle high dimensional features (hundreds of thousands to millions), a large variety of visual classes (tens of thousands to millions), and a large number of examples (millions to billions).

This workshop will consist of invited talks, panels, discussions, and paper submissions. The target audience of this workshop includes industry and academic researchers interested in machine learning, computer vision, multimedia, and related fields.

===============
Call for Papers
===============

We invite high quality submissions of extended abstracts on topics including, but not limited to

–State of the field: What really defines large scale vision? How does it differ from traditional vision research? What are its unique challenges for large scale learning?
–Indexing algorithms and data structures: How do we efficiently find similar features/images/classes from a large collection, a key operation in both recognition and retrieval?
–Semi-supervised/unsupervised learning: Large scale data comes with different levels of supervision, ranging from fully labeled and quality controlled to completely unlabeled. How do we make use of such data?
–Metric learning: Retrieval visually similar images/objects requires learning a similarity metric. How do we learn a good metric from a large amount of data?
–Visual models and feature representations: What is a good feature representation? How do we model and represent images/videos to handle tens of thousands of fine-grained visual classes?
–Exploiting semantic structures: How do we exploit the rich semantic relations between visual categories to handle a large number of classes?
–Transfer learning: How do we handle new visual classes
(objects/scenes/activities) after having learned a large number of them? How do we transfer knowledge using the semantic relations between classes?
–Optimization techniques: How do we perform learning with training data that do not fit into memory? How do we parallelize learning?
–Datasets issues: What is a good large scale dataset? How should we construct datasets? How do we avoid dataset bias?
–Systems and infrastructure: How do we design and develop libraries and tools to facilitate large scale vision research? What infrastructure do we need?
–Submissions must be in NIPS 2012 format, with a maximum number of 4 pages (excluding references).

The deadline of submission is 11:59pm PDT, September 16th, 2012.
Submissions do not have to be anonymous. Accepted papers will be presented as oral talks or posters during the workshop. For detailed submission instructions please visit https://sites.google.com/site/bigvision2012/

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

Submission deadline: September 16th, 2012.
Decision notification: October 7th, 2012.
Workshop date: December 7th or December 8th (TBD), 2012.

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

Alex Berg, Stony Brook University
Shih-Fu Chang, Columbia University
Andrew Ng, Stanford University
Florent Perronnin, Xerox Research Centre Europe
Lorenzo Torresani, Dartmouth College

==============
Organizers
==============

Samy Bengio, Google
Jia Deng, Stanford University
Fei-Fei Li, Stanford University
Yuanqing Lin, NEC Labs

Post-doc Research position on autonomously motivated exploration and skill acquisition in reinforcement learning

For the EU-funded project CompLACS
(http://www.csml.ucl.ac.uk/projects/complacs/) we are looking for a highly motivated post doctoral researcher in machine learning/reinforcement learning to develop well founded (mathematical) models for autonomous exploration and skill acquisition.

To learn more about the above project and the research at the Chair of Information Technology, University of Leoben, Austria, please visit http://institute.unileoben.ac.at/infotech.

This position will be filled in January 2013 for two years. Interviews will be conducted starting in October 2012. Highly qualified PhD candidates might be considered as well.

Applicants should submit 1) a CV, including a brief research statement,
2) 1-3 recent publications in electronic format, and 3) the names and contact information of three individuals who can serve as references.

Contact:
Univ.-Prof. Dr. Peter Auer
University of Leoben
Chair for Information Technology
Franz-Josef-Strasse 18, A-8700 Leoben, Austria
Fax: +43(3842)402-1502
E-mail: auer@unileoben.ac.at

CALL FOR ABSTRACTS AND OPEN PROBLEMS: Multi-Trade-offs in Machine Learning

NIPS-2012 Workshop, Lake Tahoe, Nevada, US
https://sites.google.com/site/multitradeoffs2012/
December 7 or 8, 2012
———————————————-
We invite submission of abstracts and open problems to Multi-Trade-offs in Machine Learning NIPS-2012 workshop.
IMPORTANT DATES
Submission Deadline: September 18.
Notification of Acceptance: October 9.
More details are provided below.
———————————————–
Abstract
One of the main practical goals of machine learning is to identify relevant trade-offs in different problems, formalize, and solve them. We have already achieved fairly good progress in addressing individual trade-offs, such as model order selection or exploration-exploitation. In this workshop we would like to focus on problems that involve more than one trade-off simultaneously. We are interested both in practical problems where “multi-trade-offs” arise and in theoretical approaches to their solution. Obviously, many problems in life cannot be reduced to a single trade-off and it is highly important to improve our ability to address multiple trade-offs simultaneously. Below we provide several examples of situations, where multiple trade-offs arise simultaneously. The goal of the examples is to provide a starting point for a discussion, but they are not limiting the scope and any other multi-trade-off problem is welcome to be discussed at the workshop.
Multi-trade-offs arise naturally in interaction between multiple learning systems or when a learning system faces multiple tasks simultaneously; especially when the systems or tasks share common resources, such as CPU time, memory, sensors, robot body, and so on. For a concrete example, imagine a robot cycling a bicycle and balancing a pole. Each task individually (cycling and pole balancing) can be modeled as a separate optimization problem, but their solutions has to be coordinated, since they share robot resources and robot body. More generally, each learning system or system component has its own internal trade-offs, which have to be balanced against the trade-offs of other systems, whereas shared resources introduce external trade-offs that enforce cooperation. The complexity of interaction can vary from independent systems sharing common resources to systems with various degrees of relation between their inputs and tasks. In multi-agent systems communication between the agents introduces an additional trade-off.
We are also interested in multi-trade-offs that arise within individual systems. For example, model order selection and computational complexity [1], or model order selection and exploration-exploitation [2]. For a specific example of this type of problems, imagine a system for real-time prediction of the location of a ball in table tennis. This system has to balance between at least three objectives that interact in a non-trivial manner: (1) complexity of the model of flight trajectory, (2) statistical reliability of the model, (3) computational requirements. Complex models can potentially provide better predictions, but can also lead to overfitting (trade-off between (1) and (2)) and are computationally more demanding. At the same time, there is also a trade-off between having fast crude predictions or slower, but more precise estimations (trade-off between (3) and (1)+(2)). Despite the complex nature of multi-trade-offs, there is still hope that they can be formulated as convex problems, at least in some situations [3].
References:
[1] Shai Shalev-Shwartz and Nathan Srebro. “SVM Optimization: Inverse Dependence on Training Set Size”, ICML, 2008.
[2] Yevgeny Seldin, Peter Auer, François Laviolette, John Shawe-Taylor, and Ronald Ortner. “PAC-Bayesian Analysis of Contextual Bandits”, NIPS, 2011.
[3] Andreas Argyriou, Theodoros Evgeniou and Massimiliano Pontil. Convex multi-task feature learning. Machine Learning, 2008, Volume 73, Number 3.
Call for Contributions
We invite submission of abstracts and open problems to the workshop. Abstracts and open problems should be at most 4 pages long in the NIPS format (appendices are allowed, but the organizers reserve the right to evaluate the submissions based on the first 4 pages only). Selected abstracts and open problems will be presented as talks or posters during the workshop. Submission instructions will be published soon.
IMPORTANT DATES
Submission Deadline: September 18.
Notification of Acceptance: October 9.
EVALUATION CRITERIA
• Theory and application-oriented contributions are equally welcome.
• All the submissions should indicate clearly at least two non-trivial trade-offs they are addressing.
• Submission of previously published work or work under review is allowed, in particular NIPS-2012 submissions. However, for oral presentations preference will be given to novel work or work that was not yet presented elsewhere (for example, recent journal publications or NIPS posters). All double submissions must be clearly declared as such!
Invited Speakers
Shai Shalev-Shwartz, The Hebrew University of Jerusalem
Jan Peters, Technicsche Universitaet Darmstadt and Max Planck Institute for Intelligent Systems
Csaba Szepesvari, University of Alberta
Organizers
Yevgeny Seldin, Max Planck Institute for Intelligent Systems and University College London
Guy Lever, University College London
John Shawe-Taylor, University College London
Koby Crammer, The Technion
Nicolò Cesa-Bianchi, Università degli Studi di Milano
François Laviolette, Université Laval (Québec)
Gábor Lugosi, Pompeu Fabra University
Peter Bartlett, UC Berkeley and Queensland University of Technology
Sponsors
Your logo could be here…. If you would like to sponsor this event, please, contact seldin@tuebingen.mpg.de.
Tentative Schedule
7:30 – 7:35 Opening remarks
7:35 – 8:20 Invited Talk
8:20 – 8:50 Two Contributed Talks
8:50 – 9:10 Break
9:10 – 9:55 Invited Talk
9:55 – 10:30 Open Problems Session
10:30 – 15:30 Break
15:30 – 16:15 Invited Talk
16:15 – 16:25 Break
16:25 – 17:00 Two Contributed Talks
17:00 – 18:30 Posters
18:30 – 19:00 Workshop Summary and Open Discussion

BMVC 2012: Prize for the Best Demo/Video/Supplementary material

Update: There will be a prize for the best demo/video/supplementary material. 3 August 2012.

BMVC 2012 offers the opportunity to showcase your research to the computer vision community.
The following two types of contributions are both encouraged:

(1) Live demonstrations showing the effectiveness of computer vision methods. These are not limited to methods described in papers that will appear at BMVC 2012. Prospective demo participants should submit the application form (http://bmvc2012.surrey.ac.uk/demo_application_bmvc12.pdf)
via email to the Demo and Video Chair. Commercial products should be presented as part of the exhibits rather than demonstrations. Accepted demonstrations will be held concurrent with the poster sessions.

(2) Any precompiled videos showing the results of computer vision related research. Videos should not exceed three minutes in length or 100MB in size. Prospective video participants should submit an FTP/HTTP link to the video via email. Videos advertising commercial products are not appropriate. Accepted videos will be shown throughout the conference.

Please be advised that at least one of the authors of each demo/video must be registered for the conference. The conference also reserves the right to select demos and videos based on the degree of appropriateness for BMVC.

24 August 2012 Demo and video submission due
27 August 2012 Demo and video notification

For further information, please contact the Demo and Video Chair.

Looking forward to your submissions,

Fei Yan, BMVC 2012 Demo and Video Chair
f.yan@surrey.ac.uk
Centre for Vision, Speech and Signal Processing, University of Surrey Guildford, United Kingdom
GU2 7XH

Assistant Professor Position at Telecom ParisTech (France)

Associate Professor in statistical learning

The group dedicated to Research in Statistics (the research group STA), within the Signal & Image processing department (the TSI Dpt.), is recruiting an Assistant Professor in the domain of statistical machine-learning. All fields related to statistical learning are of interest for the team. A specialization in reinforcement learning or optimization will be favorably considered but is not mandatory.

Research

• Academic research programs in statistical learning will be carried out.
• Research results will be published in leading journals and conferences. Activities in scientific bodies, organization of special sessions, workshops as well as involvements in committees of scientific conferences will contribute to the visibility.
• The research activities will rely on the team expertise, which covers both theoretical and methodological works in Bayesian estimation, statistical learning, reinforcement learning, and distributed statistics with collaborative computing.
• Contributing to scientific projects involving industrial partners will be done by participating to proposals to national and international research project calls, in the context of an academic chair or by co-supervising PhD theses (CIFRE thesis, involving industrial partners). The current applications considered within the group often deal with signal processing applications, which encompass forecasting, design of computer experiments, source separation, localization/tracking/cartography, control in multi-agent system.
Teaching

• In the domain of statistics and machine learning, teaching at Telecom ParisTech mainly occurs at the level of bachelor or master courses, as well as in specialized training courses. The master courses include courses in joint master with partner universities, such as MVA Master.

Skills

• Education : PhD or equivalent.
• An international postdoctoral experience is welcome but not mandatory.
• English: fluent; French: good or the candidate should be willing to improve it.

Knowledge and necessary experience

• Research publications in statistical learning (non-parametric statistics, machine learning or statistical signal processing)
• Teaching experience at the university level.

Preferred skills

• Knowledge on the numerical aspects of statistical learning and data processing.
• Theoretical or practical knowledge in optimization.
• Theoretical or practical knowledge in reinforcement learning

Other Qualities and skills

• Capacity to work in a team and develop good relationships with colleagues and peers
• Good writing and pedagogical skills

Additional information

In the context of the Paris Saclay University, activities in stochastic modeling and statistical data processing at the STA group are complementary with that conducted in the Labs LMO, CMAP and CMLA. STA and these groups are partners of the Labex LMH. The Labex
DigiWorlds also include some of the research activities of STA, for instance through partnerships with the labs LRI and LIMSI.

The position

• Permanent position
• Place of work: Paris until 2017, and then Saclay (Paris outskirt)
• For more info on being an Associate Professor at Telecom ParisTech (in French)
http://www.telecom-paristech.fr/telecom-paristech/offres-emploi-stages-theses/recrute-enseignants-chercheurs.html

Application

Candidacy are done electronically by sending a mail to
recrutement@telecom-paristech.fr

The candidacy should include :
• A complete and detailed curriculum vitae
• A letter of motivation,
• A document detailing past activities of the candidate in Teaching and Research: the two types
of activities will be described with the same level of detail and rigor.
• The text of the main publications,
• The names and addresses of two references,
• A short teaching project and a research project (maximum 3 pages)

Important dates (provisional)
• September 15 2012: application deadline

Contact :
François Roueff (Head STA group), www.telecom-paristech.fr/~roueff
Yves Grenier (Head TSI department), www.telecom-paristech.fr/~grenier/

Other web Sites :

Département Traitement du Signal et des Images: http://www.tsi.telecom-paristech.fr/
Groupe STA: http://www.tsi.telecom-paristech.fr/sta
Télécom ParisTech: http://www.telecom-paristech.fr/