PASCAL2 stands for Pattern Analysis, Statistical modelling and ComputAtional Learning 2. It is a Network of Excellence under Framework 7 (IST-2007-216886). The five year project officially started on 1st March 2008 and ends on 28th February 2013. The lists are restricted to PASCAL Members only.

Topic: ICT-2007.2.1 – Cognitive systems, interaction, robotics
Call for proposal: FP7-ICT-2007-1
Funding scheme:NoE – Network of Excellence<

PASCAL2 builds on the PASCAL Network of Excellence that has created a distributed institute pioneering principled methods of pattern analysis, statistical modelling, and computational learning. While retaining some of the structuring elements and mechanisms of its predecessor, PASCAL2 refocuses the institute towards the emerging challenges created by adaptive systems technology and its central role in the development of artificial cognitive systems of different scales. Learning technology is the key to making robots more versatile, effective and autonomous, and to endowing machines with advanced interaction capabilities.

PASCAL2 is the European Commission’s ICT-funded Network of Excellence for Cognitive Systems, Interaction & Robotics.

The PASCAL Network of Excellence has created a distributed institute pioneering principled methods of pattern analysis, statistical modeling, and computational learning as core enabling technologies for multimodal interfaces that are capable of natural and seamless interaction with and among individual human users. The resulting expertise has been applied to problems relevant to both multi-modal interfaces and cognitive systems. PASCAL2 will enable a refocusing of the Institute towards the emerging challenges created by the ever expanding applications of adaptive systems technology and their central role in the development of large scale cognitive systems. Furthermore, the funding will enable the Institute to engage in technology transfer through an Industrial Club to effect rapid deployment of the developed technologies into a wide variety of applications, while undertaking a brokerage of expertise and public outreach programme to communicate the value and relevance of the achieved results.

The PASCAL network of excellence is coordinated by John Shawe-Taylor (Scientific Coordinator) at University College London, U.K. and Steve Gunn (Operational Coordinator) at the University of Southampton, U.K.. In total there are 68 sites in the network.

University of Southampton
University College, London
University of Edinburgh
CNRS-LJK, Grenoble
CNRS-LHC, Saint-Etienne
CNRS-LRI/LM, Paris Sud
CNRS-Heudiasyc, Compiègne
CNRS-LIF, Marseille
XEROX Research Centre Europe
Jozef Stefan Institute, Ljubljana
Università degli Studi di Milano
University of Bristol
University of Manchester
University of Helsinki
Idiap Research Institute
Stichting Centrum Voor Wiskunde En Informatica
Fraunhofer-Institut – Intelligent Analysis and Information Systems
Max Planck Institut für Biologische Kybernetik
Bar Ilan University
Université Pierre et Marie Curie (Paris 6)
T U Berlin
INRIA Lille – Nord Europe
Technion, Haifa
University of Aalto
University of Sheffield
Universita dell’Insubria, Varese
Universitat d’Alicante
Budapest University of Technology and Economics
Saarland University
University of Heidelberg
Eotvos Lorand University
Università Ca’ Foscari di Venezia
Delft University of Technology
University of Amsterdam
University College Dublin
University of Surrey
Fondazione Bruno Kessler
Universität Stuttgart
Computer and Automation Research Institute of the Hungarian Academy of Sciences
University of Cambridge
Universidad Carlos III de Mardrid
University of York
University of Liege
NCSR Demokritos
Universitat Politecnica de Valencia
IMFM, Institute of Mathematics, Physics and Mechanics, Ljubljana
King’s College, London
KTH Stockholm
Leiden University
LSE, London
Technical University of Denmark
Technion, Haifa
Tel Aviv University
Graz University of Technology, Institute for Theoretical Computer Science (IGI)
Universita dell’Insubria, Varese
Universitat Pompeu Fabra
ETH Zürich
Hebrew University of Jerusalem
National ICT Australia
University of Antwerp
Katholieke Universiteit Leuven
University of Glasgow
University of Leoben
Radboud University of Nijmegen
University of Oxford
University of Sheffield
Royal Holloway, University of London
UPC Barcelona / Universidad de Cantabria
Yasemin Altun Max Planck Institut für Biologische Kybernetik
Marta Arias UPC Barcelona
elise arnaud University of Genova
Dorit Avrahami Bar Ilan University
annalisa barla University of Genova
laura bazzotti University of Genova
Florence Belmudes University of Liege
Bernadette Bouchon-Meunier Université Pierre et Marie Curie (Paris 6)
Sarah Bridle University College, London
Tamara Broderik University of Cambridge
Lorella Campanale Universita dell’Insubria, Varese
Barbara Caputo Idiap Research Institute
Barbara Caputo KTH Stockholm
Elena Casiraghi Università degli Studi di Milano
Neus Catala UPC Barcelona
Isabella Cattinelli Università degli Studi di Milano
Silvia Chiappa Max Planck Institut für Biologische Kybernetik
Gabriela Csurka XEROX Research Centre Europe
Florence d’Alché-Buc Université Pierre et Marie Curie (Paris 6)
Sophie Demassey CNRS Laboratoire d’Informatique d’Avignon
Finale Doshi University of Cambridge
Ambedkar Dukkipati EURANDOM, Eindhoven
Farida Enikeeva EURANDOM, Eindhoven
Alexandra Faynburd Technion, Haifa
Iris Fermin Aston University
Florence Forbes CNRS-LJK, Grenoble
Carolina Fortuna Jozef Stefan Institute, Ljubljana
Elisa Fromont CNRS-LHC, Saint-Etienne
Magalie Fromont CNRS-LRI/LM, Paris Sud
Pei Gao University of Manchester
Gemma Garriga Helsinki University of Technology
Elisabeth Gassiat CNRS-LRI/LM, Paris Sud
Maayan Geffet Bar Ilan University
Elisabeth Georgii Max Planck Institut für Biologische Kybernetik
Dorota Glowacka University College, London
Paula Gomes Imperial College
Dilan Gorur University College, London
manuela grindei Université Pierre et Marie Curie (Paris 6)
Isabelle Guyon CNRS-LRI/LM, Paris Sud
Isabelle Guyon ETH Zürich
Gentiane Haesbroeck University of Liege
Katja Hansen Fraunhofer-Institut für Rechnerarchitektur und Softwaretechnik
Katherine Heller University College, London
Iris Hendrickx University of Antwerp
Elena Hensinger University of Bristol
Véronique Hoste University of Antwerp
Vân Anh Huyn-Thu University of Liege
Sanaz Jabbari University of Sheffield
Stéphanie Jacquemont CNRS-LHC, Saint-Etienne
Esther Koller-Meier ETH Zürich
Efang Kong EURANDOM, Eindhoven
Petra Kralj Jozef Stefan Institute, Ljubljana
Nicole Krämer Fraunhofer-Institut für Rechnerarchitektur und Softwaretechnik
Sarit Kraus Bar Ilan University
Anastasia Krithara NCSR Demokritos
Krista Lagus Helsinki University of Technology
Tei Laine University of Helsinki
Nadia Lalam EURANDOM, Eindhoven
Raffaella Lanzarotti Università degli Studi di Milano
Nada Lavrac Jozef Stefan Institute, Ljubljana
Gayle Leen Helsinki University of Technology
Marie-Jeanne Lesot Université Pierre et Marie Curie (Paris 6)
Andrea Linhares CNRS Laboratoire d’Informatique d’Avignon
Wei Liu University of Southampton
Gaëlle Loosli INSA Rouen
Gareth Loy KTH Stockholm
Kim Luyckx University of Antwerp
Alessia Mammone University of Bristol
Talya Meltzer Hebrew University of Jerusalem
Jacqueline Meulman Leiden University
Marie-Jean Meurs CNRS Laboratoire d’Informatique d’Avignon
Luisa Mico Universitat d’Alicante
Marta Milo University of Sheffield
Dunja Mladenić Jozef Stefan Institute, Ljubljana
Roser Morante University of Antwerp
fantine mordelet Université Pierre et Marie Curie (Paris 6)
sofia mosci University of Genova
Janaina Mourão-Miranda University College, London
Vassilina Nikoulina XEROX Research Centre Europe
Maria-Elena Nilsback University of Oxford
nicoletta noceti University of Genova
francesca odone University of Genova
Francesca Odone University of Genova
Sureyya Ozogur University of Southampton
Mireille Palpant CNRS Laboratoire d’Informatique d’Avignon
Elzbieta Pekalska University of Manchester
Lyndsey Pickup University of Oxford
Ioana Popescu INSEAD, Paris
Mukta Prasad University of Oxford
Ariadna Quattoni UPC Barcelona
Myriam Rajih CNRS-Laboratoire I3S, Sophia-Antipolis
Samantha Riccadonna Fondazione Bruno Kessler
elisa ricci University of Bristol
Lorenza Romano Fondazione Bruno Kessler
Dana Ron Tel Aviv University
Sivan Sabato Hebrew University of Jerusalem
Anjali Samani University of Sheffield
Emilie Samuel CNRS-LHC, Saint-Etienne
Eerika Savia Helsinki University of Technology
Cordelia Schmid CNRS-LJK, Grenoble
Gabriele Schweikert Max Planck Institut für Biologische Kybernetik
Michele Sebag CNRS-LRI/LM, Paris Sud
Jacquelyn Shelton Max Planck Institut für Biologische Kybernetik
Nino Shervashidze Max Planck Institut für Biologische Kybernetik
Petra Šparl IMFM, Institute of Mathematics, Physics and Mechanics, Ljubljana
Eirini Spyropoulou NCSR Demokritos
Eirini Spyropoulou University of Bristol
Suwannaroj Sujimarn University of Sheffield
Josephine Sullivan KTH Stockholm
Marie Szafranski CNRS-Heudiasyc, Compiègne
Claire Tauvel CNRS-LJK, Grenoble
Jo-Anne Ting University of Edinburgh
Cristina Tirnauca UPC Barcelona
Petroula Tsampouka University of Southampton
Tinne Tuytelaars Katholieke Universiteit Leuven
Ulrike v. Luxburg Max Planck Institut für Biologische Kybernetik
Sara van de Geer ETH Zürich
Marie-Colette van Lieshout EURANDOM, Eindhoven
Kristel Van Steen University of Liege
Eleni Vasilaki University of Sheffield
Huyen-Trang Vu Université Pierre et Marie Curie (Paris 6)
Barbara Widmer ETH Zürich
Daniela Wieser University of Southampton
Sinead Williamson University of Cambridge
Young-Min Young-Min.Kim@lip6.fr Université Pierre et Marie Curie (Paris 6)
Jin Yu National ICT Australia
Huizhen Yu University of Helsinki
Karina Zapien INSA Rouen
farida zehraoui Université Pierre et Marie Curie (Paris 6)
Xiangliang Zhang CNRS-LRI/LM, Paris Sud

Gender Statistics of Researchers in PASCAL

Year 2006
Overall PASCAL Members 645
Female Researchers 40
Male Researchers 285
Female Students 50
Male Students 270
Year 2005
Overall PASCAL Members 540
Female Researchers 33
Male Researchers 241
Female Students 41
Male Students 225
Year 2004
Overall PASCAL Members 452
Female Members 60
Male Members 392
PASCAL Events Participation
Overall PASCAL participants 479
Female Researchers 31
Male Researchers 303
Female Students 16
Male Students 129

Leveraging Complex Prior Knowledge for Learning Thematic Programme
1 March – 30 September 2008

Traditionally machine learning has focused mainly on constructing models in a data driven manner. Clearly, in practise, if we can incorporate domain knowledge with our learning we should be able to obtain improved performance. This type of knowledge is particularly important in application domains where data availability is sparse in the context of the complexity of the required model. In this thematic programme we will highlight and drive forward approaches to incorporating prior knowledge in the application domain. We are interested in all approaches to incorporating this prior knowledge and any application area. Already some subthemes (and application areas) are emerging within the programme for example: knowledge encoded in graph structures (applications in language and computational biology), knowledge encoded in ordinary and stochastic differential equations (applications in climate and systems biology) and knowledge encoded as probabilities (applications in language). The Thematic Programme will run between March and September 2008 with a potential extension period to March 2009.

 Muilti-Component Learning Thematic Programme
1 October 2008 – 28 May 2010

Computer systems seldom operate in isolation and the outcome of learning tasks on one component may affect a related task on another. For example learning how best to redirect network traffic will once implemented affect the solution that should be adopted at an adjacent node. Cognitive systems composed of multiple agents are another example in which different components may be adapting their behaviour to achieve certain goals, the effects of which will influence the operating environment of other components. The design and analysis of systems involving interacting learning systems is still in its infancy, particularly when we consider theoretical analysis that can be used to guide their design, and if we include self-organisation as a design principle. A related set of challenges arise when we consider integrating information from diverse sources as for example in distributed sensor networks. Once again learning must be used to decide how to filter the data to ensure the network can provide informed responses to a range of different queries. Learning at one node of the network will influence the optimisations at other nodes. The key objective that can enable solutions in all of these applications is to build a well-founded theoretical framework analysing learning in a game theoretic setting. The learning approach can deliver the flexibility, robustness and scalability that are properties required for many applications of cognitive systems, for example in robotics. Such a framework can then provide the criteria that can be used to design and optimise multicomponent systems for a wide range of applications.

Partial or Delayed Feedback Thematic Programme
1 June 2009 – 31 December 2010

This Thematic Programme will foster research on learning models and algorithms when – in contrast to supervised learning – information about the correct predictions are not immediately available to the learner. The assumption of full information about a training instance is often unrealistic and in many applications the learner must deal with limited feedback. Although some aspects of learning with limited feedback have already been thoroughly analyzed (e.g., multi-armed bandit problems), many problems are still open.

Among others the following topics are relevant for this Thematic Programme:

  • Reinforcement learning as a model of delayed feedback, where the utility of predictions/actions might be revealed only after a number of further predictions.
  • Variants of the bandit problem as models of partial feedback, where only the utility of the learner’s predictions is available but not the utility of possible alternative predictions.
  • Models of indirect feedback, where neither the true outcome nor the utility of the prediction is observed, but only an indirect feedback loosely related to the prediction.
  • In general, the exploration-exploitation trade-off in learning models.
  • Semi-supervised and active learning.

Cognitive Architecture & Representation Thematic Programme
1 October 2009 – 28 February 2011