Open PhD position in Machine Learning and Vision (Switzerland)

The Idiap Research Institute[1], affiliated with École Polytechnique Fédérale de Lausanne[2], seeks one PhD student in statistical learning to develop original techniques for vision with complex priors.

This position is funded by a grant from the Swiss National Science Foundation, and the candidate will be a doctoral student at EPFL EDEE doctoral school[3]. Research will be done under the supervision of Dr. François Fleuret[4].

Summary:

Object detection and recognition techniques based on machine learning have historically relied on crude prior representation of the image, far from the complexity and richness of biological systems.

This project will investigate an alternative approach using very rich feature extractors addressing multiple modalities of the signal. The objective is to create new tools to help the design of such feature extractors, and to investigate learning techniques able to cope with very large and heterogeneous families of features.

The objective is to design novel approaches to full-scene interpretation, aiming at detecting many objects visible in an image.

This work will mix theoretical developments in statistical learning with the implementation of algorithms working on real-world data. Applicants must have a strong background in mathematics and be familiar with several of the following topics: probabilities, applied statistics, information theory, signal processing, optimization, algorithmic, and C++ programming.

About Idiap:

The Idiap Research Institute is located in Valais[5], a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and within close proximity to Lausanne and Geneva. The working language of Idiap is English.

Please contact francois.fleuret (at) idiap.ch for additional information.

[1] http://www.idiap.ch
[2] http://www.epfl.ch
[3] http://phd.epfl.ch/page76428.html
[4] http://www.idiap.ch/~fleuret
[5] http://maps.google.com/maps?ll=46.11323,7.003784&z=9

First CFP StReBio’09: ACM-SIGKDD workshop on Statistical and Relational Learning and mining in Bioinformatics

StReBio’09 – ACM SIGKDD workshop on Statistical and
Relational Learning and mining in Bioinformatics
http://www.cs.kuleuven.be/~dtai/events/StReBio09/
Call for contributions

OBJECTIVES
Bioinformatics is an application domain where information is naturally represented in terms of relations between heterogenous objects. Modern experimentation and data acquisition techniques allow the study of complex interactions in biological systems. This raises interesting challenges for
machine learning and data mining researchers, as the amount of data is huge, some information can not be observed, and measurements may be noisy.

The StReBio workshop aims at bringing together researchers from both the field of statistical relational learning and the field of bioinformatics. Our main goals are to provide a common venue for the two communities where biologists can present novel complex problems arising in biological applications that computer scientists could tackle by developing new statistical relational approaches.

CONTRIBUTION TYPES
We invite contributions of the following types:

* Regular papers, describing work in the area of the workshop;
* Open problem papers, describing challenges and open problems;
* Challenge solution papers, describing solutions of open problems presented at StReBio’08. A list of these problems can be found on the workshop webpage.

TOPICS OF INTEREST

The purpose of the workshop is to provide a forum for presenting and discussing new methods, problem settings, applications and models, exploiting structured data in the field of biology. Methods include, but are not restricted to

* Statistical Relational Learning
* Relational Probabilistic Models
* Multi-relational Data Mining
* Graph Methods

The data, structures or models considered can include but are not limited to

* Sequences (DNA, RNA, protein)
* Pathways (chemical, metabolic, mutation, interaction pathways)
* 2D, 3D structures of proteins, RNA
* Chemical structures (e.g. QSAR, especially regarding interaction of compounds with proteins)
* Evolutionary relations (phylogeny, homology relations)
* Ontologies integration (gene, enzyme, protein function ontologies)
* Large networks (regulatory, co-expression, interaction, metabolic,…)
* Concept graphs (heterogenuous graphs linking information on articles, authors and biological entities such as compounds, proteins, genes, …

PROCEEDINGS

ACM-SIGKDD will provide informal workshop proceedings. (Extended versions of) selected papers will be published in a special issue of Fundamenta Informaticae. Details will be published on the workshop webpage in the beginning of April.

IMPORTANT DATES

* Submission: Apr 20
* Notification: May 15
* Camera-ready copy: May 22
* Workshop: June 28

Postdoctoral Fellowships in Robotics and Adaptive Control @ Edinburgh, UK

UNIVERSITY OF EDINBURGH SCHOOL OF INFORMATICS
TWO Postdoctoral Research Fellows in Robotics and Adaptive Control

Applications are invited for two Postdoctoral Research Fellows in the area of Learning Robotics and Adaptive Control as part of an EU-IST FP7 funded project. The posts are available from Mar. 2009 for a maximum of 34 months and located in the School of Informatics at the University of Edinburgh. Salary is on the UE07 scale (£29,704-£35,469) with annual increments and full staff benefits. Placement for the post is according to experience and qualifications.

Post One: Robotics and Adaptive Control: The candidate is expected to have good fundamentals in control theory and most importantly, hands on experience with writing software and controlling robotic hardware. The appointee will be responsible for direct implementation of adaptive control paradigms on biophysical simulations and on state-of-the-art novel variable impedance actuators.

Post Two: Statistical Learning and Adaptive Control Theory: The candidate is expected to have a strong background in optimization, statistical learning and adaptive control theory and some familiarity of concepts such as direct policy learning, stochastic dynamic programming and optimal feedback control. An interest and knowledge of variable impedance strategies in human motor control is a definite advantage. The appointee will be responsible for development of effective adaptive control strategies and algorithms that exploit variable stiffness paradigms.

Both posts will involve traveling to project partner meetings around Europe, periodic reporting at EU reviews as well as attending and disseminating work at international conference. The post also assumes leadership roles and some level of PhD supervision on topics relevant to the project.

The successful candidates will have a PhD (or expected completion) in the area of (learning) robotics, probabilistic machine learning and/or adaptive motor control; strong mathematical skills in the area of optimization, algebra and control theory; strong programming skills in C, C++, MATLAB or equivalent; some experience with writing software and control of real
hardware systems; a good understanding of adaptive control paradigms

More details of the job and the research group can be found at: http://www.ipab.inf.ed.ac.uk/slmc

Applicants are asked to submit your curriculum vitae including a statement of interest justifying your suitability for the post you are applying for and contact details of two referees using the online application procedure at:

Post1:
http://www.jobs.ed.ac.uk/vacancies/index.cfm?fuseaction=vacancies.detail&vacancy_ref=3010336 Post2:
https://www.jobs.ed.ac.uk/vacancies/index.cfm?fuseaction=vacancies.detail&vacancy_ref=3010337

Application Deadline: February 20, 2009

Informal enquiries may be addressed to:
Dr. Sethu Vijayakumar (sethu.vijayakumar [at] ed.ac.uk)

Faculty job in Machine Learning at the University of Edinburgh

The School of Informatics of the University of Edinburgh invites applications for a Lectureship in Machine Learning from outstanding candidates in any area of machine learning (including models, algorithms and applications).

We particularly welcome applications from candidates who are developing principled machine learning/statistical/data mining approaches to working with real-world, complex data. Example areas include (but are not limited to): machine learning methods in computer vision/multimodal sensing; models for multi-stream data; inference and prediction in networks of interacting elements (e.g. in systems biology); reinforcement learning approaches to acting under uncertainty.

Recent investment by the Scottish Funding Council has enabled leading researchers across Scotland, including Informatics at Edinburgh, and groups and individuals at the Computer Science Departments of nine other institutions, to establish the Scottish Informatics and Computer Science Alliance (SICSA) http://www.sicsa.ac.uk. Where relevant, candidates should relate their applications to the SICSA research themes for securing, interfacing, modelling and engineering the systems of tomorrow.

[A Lectureship is roughly equivalent to a US Assistant Professor]

Informal enquiries may be addressed to Prof Chris Williams c.k.i.williams (at) ed.ac.uk .

Vacancy Ref. No: 3010479
Closing Date: 20 March 2009

For further information and to apply see https://www.jobs.ed.ac.uk/vacancies/index.cfm?fuseaction=vacancies.furtherdetails&vacancy_ref=3010479

RA position in Sheffield: probabilistic modelling in Systems Biology

A Post Doctoral Research Associate position is available in the Department of Chemical and Process Engineering for a computational scientist working on probabilistic modelling for Systems Biology. The successful candidate will join the Institute of Chemical Engineering at the Life Sciences Interface (ChELSI) in the Department of Chemical and Process Engineering. Established in 2006 following a £4.4M award from
the EPSRC, the institute is at the forefront of the development and application of systems approaches to bio-engineering. Following the appointment of two lecturers in theoretical systems biology, the institute is now seeking to further expand its modelling base. The PDRA will work with Dr Guido Sanguinetti on probabilistic modelling of high-throughput experimental data, using and developing techniques from statistical machine learning to address new problems in systems biology.
The successful applicant will have, or be in the process of obtaining, a PhD (or have equivalent experience) in a quantitative discipline (maths, physics, engineering, computer science), and will be working in a highly interdisciplinary environment. Some background in statistical data modelling and computational biology would be desirable, but motivated applicants from other numerate backgrounds are also welcome.

To apply and for further details see
http://www.jobs.ac.uk/jobs/BO379/Post_Doctoral_Research_Associate/.
Closing date is April 9th.

PhD in Machine Learning/Computational Photography

We invite applications for a Microsoft Research funded PhD scholarship based at the Max Planck Institute for Biological Cybernetics, Tuebingen.

The student will be co-supervised by Bernhard Schoelkopf (MPI Tuebingen) and Carsten Rother (Microsoft Research Cambridge) and will be working on the topic “Intrinsic Image Layers for Image Editing”. For more
information we would like to refer to the job announcement website
http://www.kyb.mpg.de/jobs/intrinsic/

Links with more information about the group at MPI,
http://www.kyb.mpg.de/bs/index.html

… Microsoft Research Cambridge,
http://research.microsoft.com/en-us/labs/Cambridge/

… and PhD scholarships from Microsoft.
http://research.microsoft.com/en-us/collaboration/global/europe/apply-europe.aspx

Call for participation: Morpho Challenge 2009

Unsupervised Morpheme Analysis — Morpho Challenge 2009
http://www.cis.hut.fi/morphochallenge2009/

Part of the EU Network of Excellence PASCAL Challenge Program and organized in collaboration with CLEF. Participation is open to all.

The objective of the Challenge is to design a statistical machine learning algorithm that discovers which morphemes (smallest individually meaningful units of language) words consist of. Ideally, these are basic vocabulary units suitable for different tasks, such as text understanding, machine translation, information retrieval, and statistical language modeling.

The scientific goals are:

* To learn of the phenomena underlying word construction in natural languages
* To discover approaches suitable for a wide range of languages
* To advance machine learning methodology

Morpho Challenge 2009 is a follow-up to our previous Morpho Challenge 2005, 2007 and 2008. The task of Morpho Challenge 2009 is similar to the Morpho Challenge 2008, where the aim was to find the morpheme analysis of the word forms in the data. There are some changes in the evaluation and a new Arabic task. New *Machine Translation* tasks are added (from Finnish to English and from German to English) to evaluate the performance of the morpheme analysis.

Participation in the previous challenges is by no means a prerequisite for participation in Morpho Challenge 2009. Everyone is welcome and we hope to attract many participating teams. The results will be presented in a workshop. Please read the rules and see the schedule at the home page. The datasets are available for download.

If you now decided to participate in Morpho Challenge, please contact the organizers and ask to be added in our mailing list. We will use this mailing list to provide news about the tasks, data and evaluations.

We are looking forward to an interesting challenge!

IDA-2009 – Final Call for Papers

IDA 2009: The eighth International Symposium on Intelligent Data Analysis

Lyon-France
August 31th, September 2nd – 2009

http://ida09.liris.cnrs.fr/

Call for Papers

Over the past decade, there has been a growing body of literature on the understanding of data analysis processes. Making smart use of the increasingly sophisticated analysis algorithms requires much expert knowledge to be part of the process itself, often in an interactive way. This knowledge is at least partially integrated into more complex data analysis meta-methods and modeling scenarios that have proven beneficial. In addition to more traditional algorithmic or application oriented submissions, IDA-2009 especially encourages submissions of papers addressing this emerging trend at the crossroads of traditional data analysis methods, complex data analysis scenarios and interactive tools that assist the analyst throughout the process. We are interested in papers describing methods that aid the analyst in the analysis procedure and we are also looking for contributions abstracting or formalizing the – often interactive – data analysis process. Contributions describing such methods should highlight potential insights into the data that the presented method offers. Examples of interesting scenarios describing steps from data to interesting models are abstractions or formalizations in terms of, for instance, generic workflows or data analysis “design patterns”. Also, description and support for interactivity in data analysis processes are of particular interest. Methods can stem from, but are not limited to, the areas of Machine Learning, Statistics, Data Mining, Artificial Intelligence, and (Interactive) Visualization.

Proceedings and venue

The maximum length of submitted papers is 12 pages in the Springer Lecture Notes in Computer Science format. The proceedings of IDA 2009 will appear in this prestigious series. Notice that Lyon will host VLDB 2009 (35th International Conference on Very Large Databases) from August 24 to August 28. Lyon is listed as a UNESCO World Heritage Site and we invite you to enjoy its splendor and its wonderful way of life.

Important dates:

Submission due: 30 March 2009
Notification of acceptance: 7 May 2009
Camera-ready copy due: 28 May 2009
Conference: August 31 – Sept 01-02 2009

Topics of interest :

Algorithms & Techniques (Machine Learning, Data Mining, Statistics):

* Artificial neural networks – Bayesian networks – Heuristic methods
* Optimization problems – Case-based reasoning – Computational models of human learning
* Computational learning theory – Cooperative learning – Unsupervised learning
* Decision and induction
* Evolutionary computation
* Grammatical inference
* Incremental and on-line learning
* Information retrieval and learning
* Knowledge acquisition and learning
* Data pre- and post-processing
* Data visualisation
* Statistical pattern recognition and analysis
* Performance and optimization
* Bootstrap and randomization
* Causal modeling
* Decision analysis
* Exploratory data analysis
* Knowledge-based analysis
* Classification, projection, regression, optimization clustering
* Data cleaning
* Model specification, selection, estimation
* Reasoning under uncertainty
* Uncertainty and noise in data

Theoritical contributions (Data analysis principles, Data modeling):

* Data Mining theories
* Information retrieval restrictions
* Legal data analysis restrictions
* Innovative data analysis (models, information types, and objectives)
* Theoretical IDA issues
* New paradigms
* Analysis of IDA algorithms

Applications Fields (Practical, Applied and Industrial Data Analysis):

* Analysis of different kinds of data (e.g., censored, temporal etc.)
* Applications (e.g., commerce, engineering, finance, legal, manufacturing, medicine, public policy, science, bioinformatics, biosurveillance)
* Assistants, intelligent agents for data analysis evaluation of IDA systems
* Human-computer interaction in IDA
* IDA systems and tools
* Information extraction, information retrieval
* Experiment design

Conference officers:

General Chair:
Jean-François Boulicaut (INSA Lyon, F)
Program Chairs:
Niall Adams (Imperial College London, UK) Céline Robardet (INSA Lyon, F)
Arno Siebes (Universiteit Utrecht, NL)
Local Organisation:
Guillaume Beslon (INSA Lyon, F)
Céline Robardet (INSA Lyon, F)
Publicity Chair:
Bruno Crémilleux (University of Caen, F)

2nd call for paper MLSP 2009

The 2009 IEEE International Workshop on MACHINE LEARNING FOR SIGNAL PROCESSING (IEEE MLSP’09) will be held in Grenoble, France next August.

You will find all relevant information about the venue, the scope and the submisison procedure on the following website: http://mlsp2009.conwiz.dk/

Formerly known as the IEEE Workshop on Neural Networks for Signal Processing, this workshop is the 19th of a very successful series of meetings. It aims at gathering all the researchers dealing with Machine
Learning, from the most advanced theoretical concepts to the most diverse applications.

Please note the the expected extended deadline for the submission of the full papers is getting closer: April 15th. For your convenience, the Latex and Word templates are already available on the website.

This year, the workshop will include some very exiting events:
– one tutorial will be given by Prof. Tulay Adali on complex-valued adaptive signal on september 1st
– one special session on “Machine Learning in Remote Sensing Data Processing” organized by Prof. Gustavo Camps Valls- one special session on “Brain-computer interfaces”, organized by José
>Millan and Marco Congedo
– one special session on “Learning in Markov models”, organized by Prof.W. Pieczynski
– one data analysis competition (http://mlsp2009.conwiz.dk/index.php?id=43)
– two outstanding pleanry speakers:
Prof. Jeanny Herault, on “Scene variability and perception constancy in the visual system: a model of pre-processing before data analysis and learning”
Prof. Lars Kai Hansen, on “Cognitive components of digital media”

ECML PKDD 2009 Call for papers – Reminder

***********************************************************
ECML PKDD 2009
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
***********************************************************

September 7-11, 2009
Bled, Slovenia
http://www.ecmlpkdd2009.net/

Key Dates
Abstract submission deadline: April 3, 2009
Paper Submission deadline: April 14, 2009
Paper Acceptance Notification: June 5, 2009
Paper Camera Ready: June 12, 2009
Call For Papers
**************

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases provides an international forum for the discussion of the latest high quality research results in all areas related to machine learning and knowledge discovery in databases. Encouraged are submissions of papers that describe the application of machine learning and data mining methods to real-world problems, particularly exploratory research that describes novel learning and mining tasks and applications requiring non-standard techniques. Submissions that demonstrate both theoretical and empirical rigor are especially encouraged.

Proceedings and Journal
***********************

The conference proceedings will be published by Springer. A selection of papers will be directly published in the special journal issues “Data Mining and Knowledge Discovery” and in “Machine Learning Journal”. All other accepted submissions will be published in the Lecture Notes in Artificial Intelligence Series.

Submissions
***********

ECML PKDD 2009 will not accept any paper which, at the time of submission, is under review or has already been accepted for publication in a journal or another conference. Authors are also expected not to submit their papers elsewhere during the review period of ECML PKDD 2009.

The papers must be in English and must be formatted according to the Springer-Verlag Lecture Notes in Artificial Intelligence guidelines.
Authors instructions and style files can be downloaded at http://www.springer.de/comp/lncs/authors.html .
The maximum length of papers is at most 16 pages in this format.
Papers submitted to ECML PKDD 2009 will normally be reviewed by minimum two referees.
There will be no “blind review” process. Student submissions should be clearly indicated on the submission form.

Organization
************

General chair:
Dunja Mladenic, Jozef Stefan Institute, Slovenia Program Chairs:
Wray Buntine, NICTA, Australia and HIIT, Finland
Marko Grobelnik, Jozef Stefan Institute, Slovenia
John Shawe-Taylor, University College London, UK

Workshop Chair: Rayid Ghani, Accenture Technology Labs, USA
Tutorial Chair: Cedric Archambeau, University College London, UK
Best Papers Chair: Aleksander Kolcz, Microsoft Live Labs, USA
Industrial track Chairs: Marko Grobelnik, Jozef Stefan Institute, Slovenia
Natasa Milic-Frayling, Microsoft Research Cambridge, UK
Discovery challenge Chair: Andreas Hotho, University of Kassel, Germany
Demo chair: Alejandro Jaimes Larrarte, Telefonica Research, Spain
Publicity chair: David R. Hardoon, University College London, UK
Video chair: Mitja Jermol, Jozef Stefan Institute, Slovenia
Local chair: Tina Anzic, Jozef Stefan Institute, Slovenia

Area Chairs: Francis Bach, Hendrik Blockeel, Francesco Bonchi, Pavel Brazdil, Toon Calders, Nitesh Chawla, Walter Daelemans, Tijl De Bie, Johannes Fuernkranz, Thomas Gaertner, Joao Gama, Bart Goethals, Eamonn Keogh, Joost Kok, Jure Leskovec, Stan Matwin, Taneli Mielikainen, Dunja Mladenic, Claire Nedellec, Martin Scholz, David Silver, Bernhard Pfahringer, Steffen Staab, Gerd Stumme, Luis Torgo, Michael Witbrock, Stefan Wrobel.