News Archives

CFP: First int. workshop on COmbining COnstraint solving with MIning and LEarning

ECAI 2012 workshop on
COmbining COnstraint solving with MIning and LEarning (CoCoMile)
http://cocomile.disi.unitn.it/2012/

Organizers: Remi Coletta (Lirmm, University of Montpellier, FR), Tias Guns
(K.U. Leuven, BE), Barry O’Sullivan (University College Cork, IR), Andrea
Passerini (University of Trento, IT), Guido Tack (Monash University, AU).

=====================
Overview:
=====================

The field of constraint solving has traditionally evolved quite
independently from those of machine learning and data mining. In recent
years, interest has been growing on the connections between these fields,
and the potential advantages of their integration. Integration can work in
two ways, on the one hand, various types of constraint solvers can be
included in machine learning and data mining algorithms, for example to
provide a uniform and effective way to characterize the desired solutions;
on the other hand, machine learning can help in addressing constraint
satisfaction problems, both at the level of search, by improving search or
integrating intelligent meta-heuristics, as well as at the level of
modelling, for example by learning constraints or interactively supporting
a decision maker.

While promising initial results have been achieved in such directions,
many options are unexplored and further research is needed in order to
establish a systematic approach to this integration. The best way to reach
the full potential of such integrations is in a multi-disciplinary way.

The main purpose of this workshop is to provide an open environment where
researchers in machine learning, data mining and constraint solving can
exchange ideas and discuss on promising approaches, crucial issues, open
problems and interesting formalizations of new
tasks.
To encourage this, we will allow three different types of submissions: 1)
original contributions (unpublished work), 2) relevant contributions
recently submitted or published elsewhere (only oral) and 3) vision
statements, works in progress and short overviews.

The following is a non-exclusive list of possible topics:
* data mining/machine learning using constraint solving techniques
* learning with constraints
* constraint-based languages for data mining/machine learning
* preference learning for constraint solving
* automated constraint modeling and solving
* constraint acquisition
* interactive constraint solving
* solver portfolio optimisation
* machine learning in search
* integrating learning and search
* automated parameter optimization / algorithm configuration

In addition to the received contributions, the workshop will include
invited talks from prominent researchers working in the intersection
between constraint technology, machine learning and data mining. The
workshop is planned to end with a broad discussion on the most relevant
open problems and research directions.

=====================
Invited speakers:
=====================

* Siegfried Nijssen (K.U. Leuven, Belgium): Constraint programming and
data mining
* Holger Hoos/Lin Xu (University of British Columbia, Canada): SATzilla:
Portfolio-based Algorithm Selection for SAT
* Francesca Rossi (University of Padova, Italy): Constrainted processing
for preference elicitation

=====================
Submission:
=====================

We accept the following three types of submissions (using ECAI-12
formatting style
http://people.cs.kuleuven.be/~luc.deraedt/ecai2012-style.zip):

* Original novel and unpublished work (max. 6 pages);

* An extended abstract of work-in-progress or position statements about
future directions, possibilities and limitations: (max. 2 pages)

* Manuscripts that have recently been accepted for publication or appeared
within the last 6 months in a peer-reviewed journal or which are currently
under review: (only oral, no page limit or format constraints)

Authors should take care that the submitted works are written at the level
of the general AI audience, and not geared towards data mining or
constraint solving expert specifically.

Submissions will be peer-reviewed by the program committee. All accepted
submissions will be published on our website (informal proceedings) unless
requested otherwise.

=====================
Important Dates:
=====================
* 28 May, 2012: submission deadline
* 28 June, 2012: notification
* 15 July, 2012: camera-ready
* 27-31 August, 2012: ECAI

=====================
Contacts:
=====================
* Remi Coletta * Tias Guns
* Barry O’Sullivan
* Andrea Passerini * Guido Tack

EPSRC/RSS GRADUATE TRAINING PROGRAMME 2012: ADVANCED COMPUTATIONAL BAYESIAN INFERENCE

Monday 23rd July 2012 – Friday 27th July 2012
School of Mathematics & Statistics, Newcastle University

This is the first of a new series of residential graduate training courses provided by the Royal Statistical Society with support from EPSRC. The courses are national and are mainly aimed at PhD students in their second and third years, though others may be able to attend. There will be two courses running sequentially:

“Modern Computational Statistics: Alternatives to MCMC”, by Professor Paul Fearnhead (Lancaster University). The course will cover Sequential Monte Carlo methods, Particle MCMC, Approximate Bayesian Computation (ABC) and automated ABC.

“Designing Markov chain Monte Carlo methods based on Diffusions and Geodesic Flows on Manifolds: The Differential Geometry of MCMC”, by Professor Mark Girolami (University College London). The course will cover Hamiltonian, Langevin and Riemannian Monte Carlo methods and their use in MCMC.

The course registration fee for GTP 2012 is £150. Accommodation and subsistence will be provided free for EPSRC-funded students from Sunday-Friday. Capacity is limited, so places on the course will be allocated on a first-come, first-served basis.

The aim of the GTP is to provide a series of high level and specialist courses in Statistics and Applied Probability to graduate Statisticians. The 2012 GTP follows on from previous successful EPSRC/RSS programmes running from 2002-2007.

FOR FURTHER INFORMATION contact gtp@ncl.ac.uk, or visit http://www.ncl.ac.uk/maths/gtp

TO REGISTER visit http://www.ncl.ac.uk/maths/gtp/registration

You may leave the list at any time by sending the command

SIGNOFF allstat

to listserv@jiscmail.ac.uk, leaving the subject line blank.

Call for Papers: AIGM’12: algorithmic issues for inference in graphical models

Web site: http://www2.toulouse.inra.fr/AIGM12
In the the framework of the ECAI’2012 conference
August 27/28 2012

Most real (e.g. biological) complex systems are formed or
modelled by elementary objects that locally interact with each
other. Local properties can often be measured, assessed or
partially observed. On the other hand, global properties that
stem from these local interactions are difficult to
comprehend. It is now acknowledged that mathematical modelling is
an adequate framework to understand, be able to control or to
predict the behaviour of complex systems, such as gene regulatory
networks or contact networks in epidemiology. More precisely,
graphical models (GM), which are formed by variables by
deterministic or stochastic relationships, allow researchers to
model possibly high-dimensional heterogeneous data and to capture
uncertainty. Analysis, optimal control, inference or prediction
about complex systems benefit from the formalisation proposed by
GM. To achieve such tasks, a key factor is to be able to answer
general queries: what is the probability to observe such event in
this situation ? Which model best represents my data ? What is
the most acceptable solution to a query of interest that
satisfies a list of given constraints ? Often, an exact
resolution cannot be achieved either because of computational
limits, or because of the intractability of the problem.

Objective

The aim of this workshop is to bridge the gap between Statistics
and Artificial Intelligence communities where approximate
inference methods for GM are developed. We are primarily
interested in algorithmic aspects of probabilistic (e.g. Markov
random fields, Bayesian networks, influence diagrams),
deterministic (e.g. Constraint Satisfaction Problems, SAT,
weighted variants, Generalized Additive Independence models) or
hybrid (e.g. Markov logic networks) models. We expect both

(i) reviews that analyze similarities and differences between
approaches developed by computer scientists and statisticians
in these areas, and

(ii) original papers that propose new algorithms and show their
performance on data sets as compared to state-of-the-art
methods.

Important dates

* Submission deadline : 31st of May
* Notification to authors: 29th of June
* Submission of final version: 13th of July

In the name of the organisation committee
N. Peyrard, S. Robin, T. Schiex

3 post-doc positions open in the SequeL group at INRIA

– Efficient Resource Allocation in Decision-Making under Uncertainty

– Time changing Markov Decision Processes

– Large scale sequential learning

More information regarding those positions, contacts, and application
are available on our website:
https://sequel.lille.inria.fr/SequeL/OpenPositions#postdocs

The postdoctoral candidate will work at SequeL lab at INRIA Lille – Nord
Europe located in Lille. SequeL is an acronym for “Sequential Learning”
and it is one of the major research groups in Europe in machine
learning, sequential learning, and multi-arm bandits. SequeL conjugates
theoretical research to applications of state-of-the-art machine
learning techniques in major IT companies in France.

If interested, please get in touch and send a detailed CV as soon as
possible. The position may start as earlier as April 2012.

Postdoc position, Statistical NLP, Univ. Politecnica Valencia

The Pattern Recognition and Human Language Technology group of the Universitat Politecnica de Valencia conducts research in Statistical Pattern Recognition, Machine Learning, Speech Recognition, Machine Translation, Image Processing and Multimodal Interaction.
The team is part of the PASCAL 2 European Network of Excellence,
ensuring a strong network of academic collaboration.

We are opening a position for a researcher with a background in the areas of Pattern Recognition, Statistical NLP, Statistical MT and/or Multimodal Interaction, to support our participation in the EU-funded project transLectures (translectures.eu).

Experience and qualifications:

– PhD with experience in at least one of the areas mentioned above.
– Good publication record in these areas.

Preferred starting date: April 2012

Contract duration: 12 months, with possible extensions.

Subject: Researcher position, Statistical NLP

More info and application instructions (in Spanish)

http://http://www.upv.es/entidades/SRH/conypi/802063normalc.html

Note: please add “In the process of applying for validation of the PhD certificate.” to your application form if your PhD certificate is not officially valid in Spain.

PASCAL2 VISIT TO INDUSTRY: CALL FOR APPLICATIONS

Deadline: MARCH 20, 2012

in order to facilitate placement and technology transfer activities, the Pascal2
Internal Visiting Program is now inviting applications for student internships
at industry organizations. This is specifically devoted to PhD and PostDoc students
who are members of Pascal2. We invite both individuals/organizations who have
previously sent in an expression of interest, as well as new ones.

The internship should last 3 to 6 months, while the host organization can in principle
be any enterprise located anywhere in the world.
See http://pascallin2.ecs.soton.ac.uk/Programmes/VP/
(VISIT TO INDUSTRY section) for details.

It is anticipated that the main use of funds under the Pascal2 Visit to Industry
stream will be to partially support travel and subsistence for the visit. The program
is not intended to cover salaries. Applications should be made by the visitor.

A Pascal2 Visit to Industry proposal should address the following main points:

– Activity description: What is the intern supposed to do ? Why is it interesting/relevant
from a scientific and/or technological viewpoint ?
Why is Machine Learning relevant to this activity ? How and to what extent
the internship is facilitating placement of the intern at the host organization ?
– Information on the host organization: Name, legal form, address, country, number
of employees, short description of enterprise activities
– Name and contact details of the person at the host organization (“tutor”) who
will be in charge of advising the intern, and help with him/her integration in the host
environment
– Content of the training (if any) that will be delivered to the intern
– Contribution granted to the intern by the host organization (e.g., accomodation,
small salary)
– Financial contribution requested to Pascal2 Visit to Industry

Proposals will be evaluated in terms of:
– Scientific and/or technological content
– Training content (if any)
– Host environment integration/placement content
– Practical support provided by the host organization to the intern
– Budget requested to Pascal2 Visit to Industry; normally the maximum
allocation will be 1000 euros per month.

Actual submissions should be done through the Pascal2 Internal Visiting Program at
http://pascallin2.ecs.soton.ac.uk/Programmes/VP/
and clicking on the Request tab.

All enquiries should be directed to: claudiogentileuninsubriait

Please send any extra material accompaying the web submission to Claudio Gentile
(claudiogentileuninsubriait) by March 20th, 2012

Call for papers – Pascal2 workshop on gesture recognition held in conjunction with CVPR

Please consider submitting a paper to the Pascal2 workshop on gesture recognition held in conjunction with CVPR (June 2012, Rhode Island, USA).

Deadline: March 16, 2012

http://gesture.chalearn.org/dissemination/cvpr2012

We will also be holding a Kinect demonstration competition, with $10’000 in prizes offered by Microsoft (proposal deadline May 1st).

Thanks in advance for your participation!

Internship – Multimodal information retrieval and summarization from Personal Electronic Health Records

Unit: TVPA

Proposers Gabriela Csurka
Mario Jarmasz
Duration: 4-6 months
Start Date: March 2012

Please see: http://www.xrce.xerox.com/About-XRCE/Internships/Multimodal-information-retrieval-and-summarization-from-Personal-Electronic-Health-Records

Software Engineer / Web Developer

Company Description
My client fuses text-mining, web analytics, social data mining, and predictive decisioning to understand and engage millions of individuals for major brands like Guinness, Unilever, and Associated News. Projects involve working with companies like Apple, Google, and the major social platforms.

My client’s team holds several patents around predictive analytics for CRM.

They have some very smart (but very fun) people in the team, and have a work hard play hard culture. Their work environment is fast-paced, very interesting, and regularly involves beer, table football and maintaining their pole position in the inter-office table tennis league. Also, they support each team member in their own personal development and training in addition they provide £2k to customize your own tech setup

Role
You will be involved with developing their core analytics platform and associated web, mobile and social apps for clients, as well as researching, designing and implementing new processes in scaling, prediction, and content analytics.

Desired Skills & Experience

Someone who:
• Can develop web applications in a cloud-based Linux/Apache/MySQL/PHP environment
• Is familiar with version control systems, specifically Git
• Is comfortable with HTML, CSS and JavaScript
• Has a degree in Computer Science or similar

Experience in:
• Test Driven Development
• Model-View-Controller frameworks, specifically CakePHP
• Emerging data store and processing technologies, such as NoSQL and Stream Processing

A deep understanding in at least one of the following topics:
• Natural Language Processing, specifically semantic extraction
• Recommendation Engines and Predictive Analytics
• Web Analytics Software and Data Mining

The ideal candidate:
• Approaches problems pragmatically, based upon a deep theoretical understanding of the underlying Computer Science concepts
• Is comfortable working in an agile environment

Benefits
• Share options
• £2k to customize your own tech setup

Please send CV and covering letter to Christine@digimobjobs.com.