PAutomaC Last Call for Participation

=================================================================
Probabilistic Automata learning Competition http://ai.cs.umbc.edu/icgi2012/challenge/Pautomac/
=================================================================
— Please, accept our apologies in case of multiple receptions —

This last call advertises that the competition data sets are available on its website since May 20th.

PAutomaC is a competition about learning probabilistic finite state models (PFA, HMM, WA, …). These machines are well-known models for characterizing the behaviour of systems or processes. Easy to interpret, their original design is usually unknown in many application fields.That is why learning approaches has been used, for instance:
– To modelize DNA or protein sequences in bioinformatics.
– To find patterns underlying different sounds for speech processing.
– To develop morphological or phonological rules for natural language processing.
– To modelize unknown mechanical processes in Physics
– To discover the exact environment of robots.
– To detect Anomaly for detecting intrusions in computer security.
– To do behavioural modelling of users in applications ranging from web systems to the automotive sector.
– To discover the structure of music styles for music classification and generation.

In all such cases, an automaton model is learned from observations of the system, i.e., a finite set of strings. As the data gathered from observations is usually unlabelled, the standard method of dealing with this situation is to assume a probabilistic automaton model, i.e., a distribution over strings.
This is what the competition is about.

*Schedule:*

– Before May 20th: training phase
– May 20th: Competition data sets are available
– June 30th: Competition is over
– July 20th: Short papers are submitted
– September 5-8th: a special session takes place duting ICGI’12 in Washington, DC, USA (http://www.coral-lab.org/icgi2012/ )

*Prizes and publications:*

Our sponsor CASL (http://http://www.casl.umd.edu/) will award a prize of
$500 to the winner of the competition.
Participants are encouraged to submit an extended abstract and to present their innovations at the PAutomaC special session that will be organised during ICGI 2012. The European network of Excellence PASCAL 2 will help best participants to travel to the conference.
The winner is expected to submit a paper to the Machine Learning Journal special issue that will follow the ICGI 2012 conference.

*Scientific committee:*

– Peter Adriaans, Universiteit van Amsterdam, The Netherlands
– Dana Angluin, Yale University, USA
– Alexander Clark, Royal Holloway University of London, UK
– Pierre Dupont, Université catholique de Louvain, Belgium.
– Ricard Gavalda, Universitat Politècnica de Catalunya, Spain
– Colin de la Higuera, Université de Nantes, France
– Jean-Christophe Janodet, Université d’Evry, France
– Tim Oates, University of Maryland Baltimore County, USA
– Jose Oncina, Universitat de Alicante, Spain
– Menno van Zaanen, Tilburg University, The Netherlands

All informations about the competition can be found on its website:
http://ai.cs.umbc.edu/icgi2012/challenge/Pautomac/
Contact email: pautomac@gmail.com

BMVC 2012 Call for *Demos and Videos*

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) and a 200 word abstract 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 and a 200 word abstract 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.

6 August 2012 Demo and video submission due
13 August 2012 Demo and video notification

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

ANNOUNCE: PASCAL Visual Object Classes Recognition Challenge 2012 (VOC2012): development kit + ECCV workshop

PASCAL Visual Object Classes Recognition Challenge 2012

We are running the PASCAL Visual Object Classes Recognition Challenge for a final time in its current form this year. There are competitions in object category classification, detection, and segmentation, and still-image action classification. A new taster competition has been introduced on action classification from approximate localization, and there is a taster competition on person layout (detecting head, hands, feet). There is also an associated large scale visual recognition taster competition organized by www.image-net.org.

We remind users that the PASCAL VOC Challenge evaluation server is available at http://host.robots.ox.ac.uk:8080/ and is currently providing evaluations and downloads for the VOC 2008-2012 challenges.

The development kit (Matlab code for evaluation, and baseline algorithms) and training/test data is now available at:

http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/index.html

where further details are given. The timetable of the challenge is:

* May 2012: Development kit (training and validation data plus
evaluation software) made available.

* 25 June 2012: Test set made available.

* 23 September 2012. Deadline for submission of results. There will be
no extensions.

* 12 October 2012: Workshop in association with ECCV 2012, Florence.

The workshop will have a new format this year, including talks from participants in the challenge, and invited talks from some of the most influential researchers in visual object recognition. See the workshop page for more information:

http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2012/workshop/index.html

Mark Everingham
Luc Van Gool
Chris Williams
John Winn
Andrew Zisserman

NIPS 2012 Call for Demonstrations

Demonstration Proposal Deadline:
Monday September 17, 2012 11:59 (UTC)

The Neural Information Processing Systems Conference 2012 http://nips.cc/Conferences/2012/ has a Demonstration Track running in parallel with the evening Poster Sessions, December 3-5, 2012, in Lake Tahoe, Nevada, USA.
Demonstrations offer a unique opportunity to showcase:
* Hardware technology
* Software systems
* Neuromorphic and biologically-inspired systems
* Robotics
* or other systems, which are relevant to the technical areas covered by NIPS
(see Call for Papers http://nips.cc/Conferences/2012/CallForPapers).

Demonstrations must show novel technology and must be run live, preferably with some interactive parts. Unlike poster presentations or slide shows, live action and interaction with the audience are critical elements.

Submissions

Submission of demo proposals at the following URL:
https://nips.cc/Demonstrators/

You will be asked to fill a questionnaire and describe clearly:
* the technology demonstrated
* the elements of novelty
* the live action part
* the interactive part
* the equipment brought by the demonstrator
* the equipment required at the place of the demo

Evaluation Criteria
Submissions will be refereed on the basis of technical quality, novelty, live action, and potential for interaction.

Demonstration chair:
Thore Graepel

Web URL: http://nips.cc/Conferences/2012/CallForDemonstrations

NIPS 2012 Call For Workshops

Natural and Synthetic NIPS*2012 Post-Conference Workshops December 7 and 8, 2012 Hotel Harrahs and Harveys Lake Tahoe, Nevada, USA

Following the regular program of the Neural Information Processing Systems
2012 conference, workshops on a variety of current topics in neural information processing will be held on December 7 and 8, 2012, in Lake Tahoe, Nevada, USA. We invite researchers interested in chairing one of these workshops to submit proposals for workshops. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are not only encouraged but preferred as workshop topics. Representation of alternative viewpoints and panel-style discussions are also particularly encouraged.

Potential workshop topics include, but are not limited to: Active Learning, Attention, Audition, Bayesian Networks, Bayesian Statistics, Benchmarking, Biophysics, Brain-Machine Interfaces, Brain Imaging, Cognitive Neuroscience, Computational Biology and Bioinformatics, Computational Complexity, Control, Graph Theory, Graphical Models, Hippocampus and Memory, Human-Computer Interfaces, Implementations, Kernel Methods, Mean-Field Methods, Music, Natural Language Processing, Network Dynamics, Neural Coding, Neural Plasticity, Neuromorphic Systems, On-Line Learning, Optimization, Perceptual Learning, Robotics, Rule Extraction, Self-Organization, Signal Processing, Social Networks, Spike Timing, Speech, Supervised/Unsupervised Learning, Time Series, Topological Maps, and Vision.

Detailed descriptions of previous workshops may be found at:
http://nips.cc/Conferences/2011/Program/schedule.php?Session=Workshops

There will be seven hours of workshop meetings per day, split into morning and afternoon sessions, with free time between the sessions for ongoing individual exchange or outdoor activities.

Workshop organizers have several responsibilities, including: Coordinating workshop participation and content, including arranging short informal presentations by experts, arranging for expert commentators to sit on discussion panels, formulating discussion topics, etc. Providing the program for the workshop in a timely manner for the workshop booklet. The expected deadline for submitting final workshop programs is October 14th, 2012. The publication date for the booklet is November 12, 2012. Moderating the discussion, and reporting its findings and conclusions to the group during the evening plenary sessions. Writing a brief summary and/or coordinating submitted material for post-conference electronic dissemination.

Submission Instructions

A nips.cc account is required to submit the Workshops application. Please follow the url below and check the required format for the application well before the deadline for workshop proposals. You can edit your application online right up until the deadline.

Interested parties must submit a proposal by
**23:59 UTC on July 6th, 2012**.

Proposals should be submitted electronically at the following URL:
https://nips.cc/Workshops/

Preference will be given to workshops that reserve a significant portion of time for open discussion or panel discussion, as opposed to a pure “mini-conference” format, and to workshops with a greater fraction of confirmed speakers.

We suggest that organizers allocate at least 50% of the workshop schedule to questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. For the same reason, we strongly recommend that each workshop includes no more than 12 talks per day.

We would like to attempt to partially unify the NIPS workshop important dates across all of the workshops. Therefore, please consider using the following date guidelines for your workshop in order to provide program information in time for publication:

* Your workshop call should be publicized on or before August 19th, 2012.
* Submission deadline should be on or before September 16th, 2012.
* Acceptance decisions mailed out on or before October 7th, 2012.

We stress that these dates are not mandatory, rather suggestions. If there are circumstances that would make your workshop difficult using these dates, you may use other dates. Also a call for contributions is not required and is orthogonal to the decision about workshop acceptance.

NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. In any case, the organizers of each accepted workshop can name two individuals to receive free registration for the workshop program.

Raquel Urtasun and Máté Lengyel
NIPS*2012 Workshops Chairs

Web URL: http://nips.cc/Conferences/2012/CallForWorkshops

Two PhD positions available on neural networks for stochastic optimal control theory on project nr 626810.

The project Neural Engineering Transformative Technologie (NETT)is a Initial Training Network funded under the EU FP7 program. The project coalesces engineering, physics and neuroscience for thedesign and development of brain-computer interface systems, cognitive computers and neural prosthetics. The project consists of 7 partners and 11 associated partners.

The NETT workpackage on adaptive control methods is coordinated by Prof. Bert Kappen at the SNN research group on Machine Learning.
The aim of the workpackage is to build neural architectures for stochastic optimal control and learning . The research is motivated by the recent work on path integral control methods. For this class of control methods, the optimal control can be computed using sampling. This approach has been shown very effective for robotics and for learning. The current project will address the questionhow such control computations can be implemented in neural networks.

SNN Machine Learning is a research group dedicated to fundamental research in the areas of machine learning and computational neuroscience. Specific topics are Bayesian networks, approximate inference methods, bio-informatics, expert systems, stochastic control and collaborative decision making. The group consists currently of 11 researchers. See www.snn.ru.nl.

SNN Machine Learning is part of the Donders Institute for Brain, Cognition and Behaviour at Radboud University Nijmegen. In the joint effort of approximately 400 researchers with backgrounds in physics, biology, medicine, genetics, psychology and the social sciences, the Donders Institute studies the relationships between brain, cognitive processes and behavior.
See www.ru.nl/donders. and www.snn.ru.nl.

The fellowship includes a three month secondment in the second year. It also includes a three month internship in the third year with the project industrial partner. Candidates must therefore be flexible and able to move between countries as necessary. This full-time post is available from the 3 September 2012 or as soon as possible thereafter and will be offered on a fixed-term contract for a period of 4 years. The maximum gross salary is € 2.379.

Requirements.

Candidates must be in the first 4 years of their research careers in physics, mathematics, engineering or computer science and not been awarded a doctorate degree. Preference will be given to candidates with experience in mathematical and computational neuroscience. As part of our commitment to promoting diversity we encourage applications from women. To comply with the Marie Curie Actions rule for mobility applicants must not have resided, worked or studied in the Netherlands for more than 12 months in the 3 years prior to Sept 2012.

The candidates will be selected on the basis of excellence, a strong theoretical background, willingness and enthusiasm to engage in multidisciplinary research; possession of relevant academic background and training; strong academic references and/or prior publications.

Application:
Applications should contain a complete CV, a brief description of your research interests and a copy of a recent publication or dissertation (optional). Applications should be sent before August 1 2012 to Personnel department, Science Faculty, University of Nijmegen, Toernooiveld 1, 6525 ED Nijmegen, the Netherlands, with reference number 626810.
Electronic submission to vacancies@science.ru.nl This e-mail address is being protected from spambots. You need JavaScript enabled to view it is acceptable.

For further information contact Prof. dr. H.J. Kappen
( b.kappen@science.ru.nl) This e-mail address is being protected from spambots. You need JavaScript enabled to view it , +31 24 3614241).

Machine Learning Developer

DeepMind is an ambitious London-based tech startup building general-purpose learning algorithms. We are funded and supported by a handful of the most successful technology entrepreneurs and investors of the past decade.

We are currently looking for an exceptionally talented software engineer to build machine learning prototypes.

Although our first commercial applications are in mobile social gaming, this role will involve working in other areas with a broader application of machine learning. The first prototype you’ll be working on is in the field of image processing.

Key Responsibilities

You’ll work closely with the business development and product team, implementing machine learning tools and technologies to help build prototypes and demonstrations. In the future, you’ll be working to develop these prototypes into enterprise quality software products, forming part of a broader team that will be built up to support the development requirements for the business. The Machine Learning you’ll be working with will initially be focused on image processing and after this you’ll be working in a range of possible application areas such as prediction, search, control and perception.

About You

You have a real thirst for knowledge and a keen analytical mind as well as a real passion for new technology.

You have a good class degree, ideally in machine learning, artificial intelligence, computer science,
mathematics or physics and an aptitude for problem solving. Experience with image processing (such as image search, image matching and CBIR — content based image retrieval) is highly desirable. You should be a strong Python coder, and experience in other languages (such as Matlab, PHP, Java, SQL and C / C++) would be an advantage.

You should be self-motivated and a good team player with excellent communication skills.

Ideally, you will have machine learning experience in an academic or commercial environment, and will have experience of building and experimenting with a range of machine learning techniques, including image processing. Ideally, you will have experience of some or all of the following tools and methods:

● Neural networks and support vector machines
● Text processing
● Data mining
● K-Means clustering
● Genetic algorithms
● Algorithm design

This is a full-time, permanent position, based in London. Salary range: £35,000 to £45,000 + share options.

Please send us a paragraph about yourself and a CV: jobs@deepmind.com

Course for the “Pattern Recognition in Neuroimaging Toolbox”, aka. PRoNTo

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Course for the “Pattern Recognition in Neuroimaging Toolbox”, aka. PRoNTo
21 May 2012

Dear colleagues,

We are pleased to announce that registration for the first PRoNTo(*) course 2012 is now open.

This one-day course will be held for the first time in London and will offer a comprehensive coverage of all “Pattern Recognition for Neuroimaging Toolbox” features and functionalities, including:

– introduction to neuroimaging and machine learning concepts

– specific pattern recognition methods for neuroimaging

– hands on session

For further information and registration, please see:

http://www.mlnl.cs.ucl.ac.uk/pronto/prtcourses.html

Sincerely,
Janaina Mourao-Miranda

(*) PRoNTo aims to facilitate the interaction between the machine learning and neuroimaging communities. The toolbox provides a variety of tools for the neuroscience and clinical neuroscience communities, enabling these communities to ask new questions that cannot be easily investigated using existing statistical analysis tools. On the other hand the machine learning community can easily contribute to the toolbox with novel published machine learning algorithms. PRoNTo is directly compatible with SPM8.
See http://www.mlnl.cs.ucl.ac.uk/pronto/ for more details and download.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

First CFP – Data Streams Track – ACM SAC 2013

========================================================================
ACM SAC 2013
The 28th Annual ACM Symposium on Applied Computing
in Coimbra, Portugal, March 18-22, 2013.
http://www.acm.org/conferences/sac/sac2013/

DATA STREAMS TRACK
http://www.cs.waikato.ac.nz/~abifet/SAC2013/
========================================================================

CALL FOR PAPERS

The rapid development in information science and technology in general
and in growth complexity and volume of data in particular has
introduced new challenges for the research community. Many sources
produce data continuously. Examples include sensor networks, wireless
networks, radio frequency identification (RFID), health-care devices
and information systems, customer click streams, telephone records,
multimedia data, scientific data, sets of retail chain transactions,
etc. These sources are called data streams. A data stream is an
ordered sequence of instances that can be read only once or a small
number of times using limited computing and storage capabilities.
These sources of data are characterized by being open-ended, flowing
at high-speed, and generated by non stationary distributions.

TOPICS OF INTEREST
We are looking for original, unpublished work related to algorithms,
methods and applications on data streams. Topics include (but are not
restricted) to:

– Data Stream Models
– Languages for Stream Query
– Continuous Queries
– Clustering from Data Streams
– Decision Trees from Data Streams
– Association Rules from Data Streams
– Decision Rules from Data Streams
– Bayesian networks from Data Streams
– Feature Selection from Data Streams
– Visualization Techniques for Data Streams
– Incremental on-line Learning Algorithms
– Single-Pass Algorithms
– Temporal, spatial, and spatio-temporal data mining
– Scalable Algorithms
– Real-Time and Real-World Applications using Stream data
– Distributed and Social Stream Mining

IMPORTANT DATES (strict)
1. Paper Submission: September 21, 2012
2. Author Notification: November 10, 2012
3. Camera‐ready copies: November 30, 2012

PAPER SUBMISSION GUIDELINES
Papers should be submitted in PDF using the SAC 2013 conference
management system: http://www.softconf.com/c/sac2013/. Authors are
invited to submit original papers in all topics related to data
streams. All papers should be submitted in ACM 2-column camera ready
format for publication in the symposium proceedings. ACM SAC follows a
double blind review process. Consequently, the author(s) name(s) and
address(s) must NOT appear in the body of the submitted paper, and
self-references should be in the third person. This is to facilitate
double blind review required by ACM. All submitted papers must include
the paper identification number provided by the eCMS system when the
paper is first registered. The number must appear on the front page,
above the title of the paper. Each submitted paper will be fully
refereed and undergo a blind review process by at least three
referees. The conference proceedings will be published by ACM. The
maximum number of pages allowed for the final papers is 6 pages. There
is a set of templates to support the required paper format for a
number of document preparation systems at:
http://www.acm.org/sigs/pubs/proceed/template.html

For accepted papers, registration for the conference is required and
allows the paper to be printed in the conference proceedings.
An author or a proxy attending SAC MUST present the paper. This is a
requirement for the paper to be included in the ACM Digital Library.
No-show of scheduled papers will result in excluding the papers from
the ACM Digital Library.

STUDENT RESEARCH COMPETITION
Graduate students seeking feedback from the scientific community on
their research ideas are invited to submit abstracts of their original
un-published and in-progress research work in areas of experimental
computing and application development related to SAC 2013 Tracks. The
Student Research Competition (SRC) program is designed to provide
graduate students the opportunity to meet and exchange ideas with
researcher and practitioners in their areas of interest. All research
abstract submissions will be reviewed by researchers and practitioners
with expertise in the track focus area to which they are submitted.
Authors of selected abstracts will have the opportunity to give poster
presentations of their work and compete for three top wining places.
The SRC committee will evaluate and select First, Second, and Third
place winners. The winners will receive cash awards and SIGAPP
recognition certificates during the conference banquet dinner. Authors
of selected abstracts are eligible to apply to the SIGAPP Student
Travel Award program for support. Graduate students are invited to
submit abstracts (minimum of two pages; maximum of four pages)
of their original un-published and in-progress research work following
the instructions published at SAC 2013 website. The submissions must
address research work related to a SAC track, with emphasis on the
innovation behind the research idea, including the problem being
investigated, the proposed approach and research methodology, and
sample preliminary results of the work. In addition, the abstract
should reflect on the originality of the work, innovation of the
approach, and applicability of anticipated results to real-world
problems. All abstracts must be submitted thought the START Submission
system. Submitting the same abstract to multiple tracks is not allowed.
If you encounter any problems with your submission, please contact
the Program Chairs.

Harvest Programme Call – Spring 2012

Do you have a good idea for some really cool software, useful and/or
fun for people out there, but you are missing the team, the money, or
the place?

This announcement is for you: read it carefully!

***********************************************************************
***********************************************************************
*** PASCAL2 invites submissions of proposals for Harvest Projects ***
***********************************************************************
***********************************************************************
********************** Important dates ********************************

– Expression of intention to submit: June 15, 2012
– Deadline proposal submissions: June 29, 2012
– Notification of acceptance: August 17, 2012

Inquiries: anytime.

Notes: the total budget for this call is euros 35k. This is the last
Call for Harvest projects!

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

There are many innovative things we would be able to do, but we never
find the time, we don’t have the money, students/programmers are
needed and hard to find. Still it would be real fun to devise a smart
code, to see people using it, and to have your name on the Pascal Hall
of Fame 🙂 The Pascal Harvest Programme aims at making it possible,
easy, and rewarded. The main idea behind Harvest is: put together in a
room a team for long enough to produce an innovative software for a
real application. PASCAL2 will pick up the bills.

Sounds interesting? Please check out all you need to know on the
programme website:

(Internal) http://pascallin2.ecs.soton.ac.uk/Programmes/HA/
(External) http://www.pascal-network.org/?q=node/19

For this call we are open to all three scenarios in:

http://pascallin2.ecs.soton.ac.uk/Programmes/HA/harvest_webpage.html#IP
http://www.pascal-network.org/?q=node/19#ipr

————————————————————————

A Harvest project proposal should address the following points in 4-8
pages:

* Problem description: what is the project going to do? Why is it
interesting? Why is Machine Learning relevant?
* Specification and validation. How do we assess performance?
* Expected staffing, location and duration. How many persons will be
needed? For how long?
* Milestones, timeline.
* Requested funding.
* Content of the training, if any, that will be delivered to
participants.

An example proposal can be downloaded from the programme website.
There is no expectation that the team is fully identified at the time
of the proposal submission.

Proposals will be evaluated by independent experts. Criteria used in
the evaluation will be:

* Application interest: is this going to be useful to someone?
* State of the art: is the problem still challenging for
scientific/technical/other reasons? Not challenging still not done
yet? Might it lead also to a good paper?
* Impact outside PASCAL: will anyone outside the machine-learning,
optimization and statistics community like it? Can this be viewed
as a generic proof of principle? Of what?
* Training: will junior participants learn interesting and useful
things?
* Management and planning: is the project going to deliver on its
promises?
* Timeliness: can you make this happen soon?

For this Call we will ask reviewers to assess proposals with an eye to
the approaching conclusion of the EC funding for the PASCAL 2 network:
will the project contribute an interesting demo? Will it create some
important legacy? Something that can have its own life after the end
of the network?

Unlike in previous calls, proposals requesting funding to cover some
limited expenses for personnel salaries can also be considered. For
administrative reasons, however, this possibility is limited to
personnel of PASCAL 2 Beneficiary members only.

An email stating the intention to submit a proposal should be
addressed to Nicola dot Cancedda at xrce dot xerox dot com and sebag
at lri dot fr by June 15th, 2012. Actual submissions should be done
through the PASCAL2 Harvest Programme page by June 29th, 2012:

http://pascallin2.ecs.soton.ac.uk/Programmes/HA/Request/

For all inquiries please write to Nicola dot Cancedda at xrce dot
xerox dot com and sebag at lri dot fr.