Liste de nos séminaires
(ordre antichronologique)
Séminaire DAPA du 28 / 5 / 2015 à 10h
Does it all add up? A study of fuzzy protoform linguistic summarization of time series
Jim Keller (University of Missouri (USA))
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Producing linguistic summaries of large databases or temporal sequences of measurements is an endeavor that is receiving increased attention. These summaries can be used in a continuous monitoring situation, like eldercare, where it is important to ascertain if the current summaries represent an abnormal condition. Primarily a human, such as a care giver in the eldercare
example, is the recipient of the set of summaries describing a time range, for example, last night’s activities. However, as the number of sensors and monitored conditions grow, sorting through a fairly large number of summaries can be a burden for the person, i.e., the summaries stop being information and become yet one more pile of data. It is therefore necessary to automatically process sets of summaries to condense the data into more manageable chunks.
The first step towards automatically comparing sets of digests is to determine similarity. For fuzzy protoform based summaries, we developed a natural similarity and proved that the associated dissimilarity is a metric over the space of protoforms. Utilizing that distance measure, we defined and examined several fuzzy set methods to compute dissimilarity between sets of summaries, and most recently utilized these measures to define prototypical behavior over a large number of normal time periods.
In this talk, I will cover the definition of fuzzy protoforms, define our (dis)similarity, outline the proof that it is a metric, discuss the fuzzy aggregation methods for sets of summaries, and show how prototypes are formed and can used to detect abnormal nights. The talk will be loaded with actual examples from our eldercare research. There is much work to be done and hopefully, more questions than answers will result from the discussion.
Sponsored by the Computational Intelligence Society under its Distinguished Lecturer Program
James M. Keller is a Curators Professor in the Electrical and Computer Engineering and Computer Science departments at the University of Missouri as well as R. L. Tatum Professor for the college. Keller’s research interests are in computational intelligence with current applications to eldercare technology, bioinformatics, geospatial intelligence and landmine detection.
James M. Keller is a CIS Distinguished Lecturer.
Plus d'information sur Jim Keller : http://engineering.missouri.edu/person/kellerj/
Séminaire DAPA du 12 / 3 / 2015 à 14h
Grille bivariée pour la détection de changement dans un flux étiqueté
Vincent Lemaire (Orange Labs)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Cet exposé présentera :

le contexte de la détection de concept drift dans un flux étiqueté : en analyse prédictive et en apprentissage automatique, on parle de dérive conceptuelle lorsque les propriétés statistiques de la variable cible, que le modèle essaie de prédire, évoluent au cours du temps d'une manière imprévue. Ceci pose des problèmes parce que les prédictions deviennent moins exactes au fur et à mesure que le temps passe. La dérive conceptuelle est une des contraintes en fouille de flux de données.

une méthode enligne de détection de changement de concept dans un flux étiqueté : elle est basée sur un critère supervisé bivarié qui permet d’identifier si les données de deux fenêtres proviennent ou non de la même distribution. Notre méthode a l’intérêt de n’avoir aucun a priori sur la distribution des données, ni sur le type de changement et est capable de détecter des changements de différentes natures (changement dans la moyenne, dans la variance...). Les expérimentations montrent que notre méthode est plus performante et robuste que les méthodes de l’état de l’art testées.
Vincent Lemaire is a senior expert in datamining. His research interests are the application of machine learning in various areas for telecommunication companies with an actual main application in data mining for business intelligence. He developed exploratory data analysis and classification interpretation tools.
Plus d'information sur Vincent Lemaire : http://www.vincentlemairelabs.fr/
Séminaire DAPA du 15 / 1 / 2015 à 14h
Tensor factorization for multirelational learning
Raphael Bailly (Heudiasyc, Université Technologique de Compiègne, France)
Lieu : salle 101, couloir 2526, 4 place Jussieu, 75005 Paris
Learning relational data has been of a growing interest in fields as diverse as modeling social networks, semantic web, or bioinformatics. To some extent, a network can be seen as multirelational data, where a particular relation represents a particular type of link between entities. It can be modeled as a threeway tensor.
Tensor factorization have shown to be a very efficient way to learn such data. It can be done either in a 3way factorization style (trigram, e.g. RESCAL) or by sum of 2way factorization (bigram, e.g TransE). Those methods usually achieve stateoftheart accuracy on benchmarks. Though, all those learning methods suffer from regularization processes which are not always adequate.
We show that both 2way and 3way factorization of a relational tensor can be formulated as a simple matrix factorization problem. This class of problems can naturally be relaxed in a convex way. We show that this new method outperforms RESCAL on two benchmarks.
R. Bailly is currently postdoc at Heudiasyc (since march 2014), Compiègne. He works with Antoine Bordes and Nicolas Usunier on multirelational learning and word embeddings. He was previously in Barcelona for a postdoc with Xavier Carreras, whith whom he worked on spectral methods applied to unsupervised setting.
Plus d'information sur Raphael Bailly : https://www.hds.utc.fr/~baillyra/
Séminaire DAPA du 27 / 11 / 2014 à 10h
The FrankWolfe Algorithm: Recent Results and Applications to HighDimensional Similarity Learning and Distributed Optimization
Aurélien Bellet (Télécom ParisTech)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
The topic of this talk is the FrankWolfe (FW) algorithm, a greedy procedure for minimizing a convex and differentiable function over a compact convex set. FW finds its roots in the 1950's but has recently regained a lot of interest in machine learning and related communities. In the first part of the talk, I will introduce the FW algorithm and review some recent results that motivate its appeal in the context of largescale learning problems. In the second part, I will describe two applications of FW in my own work: (i) learning a similarity/distance function for sparse highdimensional data, and (ii) learning sparse combinations of elements that are distributed over a network.
Aurélien Bellet is currently a postdoc at Télécom ParisTech. Previously, he worked as a postdoc at the University of Southern California and received his Ph.D. from the University of SaintEtienne in 2012. His main research topic is statistical machine learning, with particular interests in metric/similarity learning and largescale/distributed learning.
Plus d'information sur Aurélien Bellet : http://perso.telecomparistech.fr/~abellet/
Séminaire DAPA du 13 / 11 / 2014 à 10h
ComputerAided Breast Tumor Diagnosis in DCEMRI Images
Baishali Chaudhury (Department of Computer Science and Engineering, University of South Florida)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
The overall goal of our project is to quantify tumor heterogeneity with advanced image analysis to provide useful information about tumor biology and provide unique and valuable insight into patient treatment strategies and prognosis.We introduced a CAD (computer aided diagnosis) system to characterize breast cancer heterogeneity through spatiallyexplicit maps using DCEMRI images. Through quantitative image analysis, we examined the presence of differing tumor habitats defined by initial and delayed contrast patterns within the tumor. The heterogeneity within each habitat was quantified through textural kinetic features at different scales and quantization levels. The functionality of this CAD system was then evaluated by applying it in a multiobjective framework. Various common problems in breast DCEMRI analysis (like extremely small dataset compared to the number of extracted texture features and highly imbalanced dataset) and different data mining techniques applied in our project to deal with them will be discussed.
Fourth year PhD Candidate in University of South Florida, Tampa, USA. Currently, working on the “Analysis of DCEMRI breast tumor images for stratifying patient prognosis”. Broader research interests include: computer vision, data mining and machine learning, sparse data representation.
Plus d'information sur Baishali Chaudhury : http://baishalichaudhury.wix.com/baishali
Séminaire DAPA du 30 / 10 / 2014 à 11h
WaterFowl: a Compact, SelfIndexed RDF Store based on Succinct Data Structures
Olivier Curé (Laboratoire d'informatique GaspardMonge, Université MarnelaVallée)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 2 / 10 / 2014 à 10h
Subgoal Discovery and Language Learning in Reinforcement Learning Agents
Marie desJardins (Department of Computer Science and Electrical Engineering at the University of Maryland, USA)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
As intelligent agents and robots become more commonly used, methods to make interaction with the agents more accessible will become increasingly important. In this talk, I will present a system for intelligent agents to learn task descriptions from linguistically annotated demonstrations, using a reinforcement learning framework based on objectoriented Markov decision processes (OOMDPs). Our framework learns how to ground natural language commands into reward functions, using as input demonstrations of different tasks being carried out in the environment. Because language is grounded to reward functions, rather than being directly tied to the actions that the agent can perform, commands can be highlevel and can be carried out autonomously in novel environments. Our approach has been empirically validated in a simulated environment with both expertcreated natural language commands and commands gathered from a user study.
I will also describe a related, ongoing project to develop novel option discovery methods for OOMDP domains. These methods permit agents to identify new subgoals in complex environments that can be transferred to new tasks. We have developed a framework called Portable Multipolicy Option Discovery for Automated Learning (PMODAL), an approach that extends the PolicyBlocks option discovery approach to OOMDPs.
This work is collaborative research with Dr. Michael Littman and Dr. James MacGlashan of Brown University, Dr. Smaranda Muresan of Columbia University. A number of UMBC students have contributed to the project: Shawn Squire, Nicholay Topin, Nick Haltemeyer, Tenji Tembo, Michael Bishoff, Rose Carignan, and Nathaniel Lam.
Dr. Marie desJardins is a Professor in the Department of Computer Science and Electrical Engineering at the University of Maryland, Baltimore County, where she has been a member of the faculty since 2001. She is a 201314 American Council of Education Fellow, the 201417 UMBC Presidential Teaching Professor, and an inaugural Hrabowski Academic Innovation Fellow. Her research is in artificial intelligence, focusing on the areas of machine learning, multiagent systems, planning, interactive AI techniques, information management, reasoning with uncertainty, and decision theory. Current research projects include learning in the context of planning and decision making, analyzing and visualizing uncertainty in machine learning, trust modeling in multiagent systems, and computer science education.
Dr. desJardins has published over 120 scientific papers in journals, conferences, and workshops. She is an Associate Editor of the Journal of Artificial Intelligence Research, is a member of the editorial board of AI Magazine, and was the Program Cochair for AAAI13. She has previously served as AAAI Liaison to the Board of Directors of the Computing Research Association, ViceChair of ACM's SIGART, and AAAI Councillor. She is an ACM Distinguished Member, is a AAAI Senior Member, holds an appointment at the University of Maryland Institute for Advanced Studies, is a member and former chair of UMBC's Honors College Advisory Board, is the former chair of UMBC's Faculty Affairs Committee, and serves on the advisory board of UMBC's Center for Women in Technology.
Plus d'information sur Marie desJardins : http://www.csee.umbc.edu/~mariedj/
Séminaire DAPA du 11 / 9 / 2014 à 14h
Clusteringbased Models from Modelbased Clustering
Mika SatoIlic (Faculty of Engineering, Information and Systems. University of Tsukuba)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 3 / 7 / 2014 à 10h
Clustering de données temporelles, application à l'analyse des données issue des médias sociaux
Julien Velcin
laboratoire ERIC, Université Lyon 2
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 1 / 7 / 2014 à 17h
PLUIE (Probability and Logic Unified for Information Extraction): Interim Report
Stuart Russell (University of California, Berkeley)
Ole Torp Lassen (LIP6, UPMC)
Wei Wang (LIP6, UPMC)
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
The goal of the PLUIE project is to investigate an old approach to
understanding language: the idea that declarative text expresses
information about the world. This idea is captured in the form of a
probability model that describes how sentences are generated from
worlds. A very simple model of this kind exhibits a number of
interesting properties including robust bootstrap inferences and
relation discovery. The talk will summarize the approach and cover two
specific subproblems: efficient splitmerge MCMC inference in an
entitymention model and flexible mention grammars for named entities.
S. Russell est soutenu par, et cette présentation est donnée sous les auspices de, la Chaire Internationale de Recherche Blaise Pascal, financée par l'Etat et la Région Île de France, gérée par la Fondation de l'Ecole Normale Supérieure.
Séminaire DAPA du 5 / 6 / 2014 à 14h
Classification nonsupervisée recouvrante par kmoyennes revisité
Guillaume Cleuziou
IUT Informatique d'Orléans
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 22 / 5 / 2014 à 10h
Collaborative activity in learning situations: forms and processes
Michael Baker
CNRS
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 15 / 5 / 2014 à 10h
A normal hierarchical model for random intervals / The silhouette index  an extension to fuzzy clustering and applications to feature selection
Dan Ralescu / Anca Ralescu
Department of Mathematical Sciences, University of Cincinnati, USA / Computer Sciences, EE & CS Dept. College of Engineering University of Cincinnati, USA
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
(10h3011h20) Dan Ralescu, Professor, Department of Mathematical Sciences, University of Cincinnati, USA
A normal hierarchical model for random intervals
Existing methods for analyzing intervalvalued data include regressions in the metric space of intervals and symbolic data analysis, the latter being proposed in a more general setting. However, there has been a lack of literature on the parametric modeling and distributionbased inferences for intervalvalued data.
(11h2012h10) Anca Ralescu, Professor, Computer Sciences, EE & CS Dept. College of Engineering University of Cincinnati, USA
The silhouette index  an extension to fuzzy clustering and applications to feature selection
Séminaire DAPA du 20 / 2 / 2014 à 10h
Robust recommendations and their explanation in multicriteria decision aiding
Christophe Labreuche
Thales Group, France
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
MultiCriteria Decision Aid (MCDA) aims at helping an individual to make choices among alternatives described by several attributes, from a (small) set of learning data representing her preferences. MCDA has a wide range of applications in smart cities, engineering, recommender systems and so on. Among the variety of available decision models, one can cite the weighted majority, additive utility, weighted sum or the Choquet integral.
Once the expression of the decision model has been chosen, the generation of choices among alternatives is classically done as follows. In a constraint approach, from a set of learning data (representing for instance comparisons of alternatives), one then looks for the value of the model parameters compatible with the learning data, which maximizes some functional, e.g. an entropy or a separation variable on the learning data. The comparisons among alternatives are then obtained by applying the model with the previously constructed parameters. The major difficulty the decision maker faces is that there usually does not exist one unique value of the parameters compatible with the learning data. Hence this approach introduces much arbitrariness since the generated preferences are much stronger than the learning data.
Robust preference relations have been recently introduced in MCDA to overcome this difficulty. An alternative is said to be necessarily preferred to another one if the first one dominates the second for any value of the parameters compatible with the learning data. In Artificial Intelligence, this operator is often called entailment. It is actually a closure operator. This necessity preference relation is usually incomplete, unless the model is completely specified from the preferential information of the decision maker.
The introduction of robust preference relation brings many new challenges:
 algorithmic aspects: how to design efficient algorithms to construct it?
 explanation: how to explain to the decision maker the recommended robust preferences? In other words, how are the recommendations derived from the learning data?
We will address these points in the talk.
Séminaire DAPA du 6 / 2 / 2014 à 10h
Apprentissage actif en classification évidentielle sous contraintes
Violaine Antoine
ISIMA Limos
Lieu : salle 101, couloir 2526, 4 place Jussieu, 75005 Paris
La classification évidentielle et non supervisée se caractérise par l'utilisation de fonctions de croyance, et notamment l'utilisation de la notion de partition crédale. Cette notion élargit le concept de partition nette, floue, probabiliste ou possibiliste. Ainsi, elle permet de mesurer de manière précise l'incertitude quant à l'affectation d'un objet à une classe.
La classification sous contraintes, également appelée classification semisupervisée, est une approche qui introduit une connaissance a priori sous forme de contraintes sur la partition recherchée. Nous nous intéressons ici à des contraintes au niveau des objets : une contrainte MustLink spécifie que deux objets doivent être dans la même classe alors qu'une contrainte Cannotlink indique que deux objets se trouvent dans des classes différentes. L'ajout de contraintes permet une amélioration sensible des résultats de classification. Néanmoins, dans le cadre d'applications réelles, il est parfois difficile d'obtenir un jeu de contraintes intéressant. L'apprentissage actif consiste donc à obtenir ces informations à moindre coût.
Dans cette présentation, nous proposons deux nouveaux algorithmes de classification sous contraintes utilisant le cadre théorique des fonctions de croyance. Grâce à la partition crédale qu'ils retournent, nous pouvons identifier de manière précise les objets problématiques pour la classification. Un nouvel algorithme d'apprentissage actif est alors proposé afin de réduire l'erreur de classification.
Séminaire DAPA du 19 / 12 / 2013 à 10h
The raise of graph databases/dataspaces and their relations with Linked Data and Ontologies
André Santanchè
Universidade Estadual de Campinas, Brazil
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Séminaire DAPA du 16 / 12 / 2013 à 16h
Extended Logic Programming and Intelligent System Development
Asushi INOUE
University of Cincinnati
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
A longterm effort toward a general application framework
for intelligent systems is introduced. Many intelligent systems
adopt a knowledgebased system architecture, and their development
thus differs from other application development. Expressing knowledge
as rules shifts one's perspective from data manipulation to relation
investigation. Our recent progress about two components are focused
 Extended Logic Programming (ELP), i.e. the keystone of this framework,
and a multiview visualization scheme in order to effectively and
efficiently visualize the reasoning processes of ELP. Few representative
applications are showcased as time allows.
Reference:
K. Springer, M. Henry, A. Inoue, "A General Application Framework for Intelligent Systems,"
The 20th Midwest Artificial Intelligence and Cognitive Science Conference (MAICS2009),
Fort Wayne, IN, pp. 188195, 2009.
Séminaire DAPA du 5 / 12 / 2013 à 10h
Granular Models for Time Series Forecasting
Rosangela Ballini
Institute of Economics, University of Campinas, Brazil
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
time series forecasting. These models are constructed in two phases.
The first one uses the clustering algorithms to find group structures in a
historical database. Two different approaches are discussed: fuzzy cmeans
clustering and participatory learning algorithms. Fuzzy cmean clustering,
which is a supervised clustering algorithm, is used to explore similar
data characteristics, such as trend or cyclical components. Participatory
learning induces unsupervised dynamic fuzzy clustering algorithms and
provides an effective alternative to construct adaptive fuzzy systems.
In the second phase, two cases are considered. In the first case, a
regression model is adjusted for each cluster and forecasts are produced
by a weighted combination of the local regression models. In the second
case, prediction data are classified according to the group structure
found in the database. Then, forecasts are produced using the cluster
centers weighted by the degree with which prediction data match the
groups. The weighted combination of local models constitutes a forecasting
approach called granular functional forecasting modeling, and the approach
based on weighted combination cluster centers comprises granular
relational forecasting modeling. The effectiveness of the granular
forecasting approaches is verified using three different applications:
average streamflow forecasting, pricing option estimation and modeling of
regime changes in Brazilian nominal interest rates.
Séminaire DAPA du 7 / 11 / 2013 à 10h
Automated Feature Weighting in Naive Bayes for Highdimensional Data Classification
Shengrui Wang
Université de Sherbrooke
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
This talk is about our recent work in the area of feature weighting for high dimensional data classification (and clustering). The first part of my talk relates to Naive Bayes (NB for short) classifier. Currently, in many realworld applications, highdimensionality poses a major challenge to conventional NB classifiers, due to noisy or redundant features and local relevance of these features to classes. In this work, we propose an automated feature weighting solution to enable the NB method to deal effectively with highdimensional data. First a locally weighted probability model will be presented for implementing a soft feature selection scheme. Then an optimization algorithm will be presented to find the weights in linear time complexity, based on the Logitnormal priori distribution and the Maximum a Posteriori principle. Experimental studies will show the effectiveness and suitability of the proposed model for highdimensional data classification.
In the second part of this talk, I will briefly present our work on central clustering of categorical data with automated feature weighting. A novel kerneldensitybased definition of cluster center is proposed using a Bayestype probability estimator. Then, an algorithm called kcenters is proposed incorporating a new feature weighting scheme by which each attribute is automatically assigned with a weight measuring its individual contribution for the clusters.
Séminaire DAPA du 4 / 11 / 2013 à 10h
Abductive reasoning made easy with Prolog and Constraint Handling Rules
Henning Christiansen
Roskilde University
Lieu : salle 105, couloir 2526, 4 place Jussieu, 75005 Paris
Abductive reasoning, or "abduction", means to find a best explanation for some unexpected observation. In a logical setting, an explanation can be a set of facts which, when added to our current knowledge base, makes it possible to prove the truth of the observation and, at the same time, is not inconsistent with the knowledge base. Abduction in this sense is a useful metaphor for many sorts of reasoning aiming at answering "why" or "what" questions such as medical diagnosis, language understanding and decoding of biological sequence data. Furthermore, models of abductive reasoning can lead to practical implementation techniques.
Introduced by Peirce, the notion has attracted much attention in philosophy, detective stories and computer science, most notably in logic programming. Until the shift of the millennium, abduction in logic programming was realized through complex metainterpreters written in Prolog, which may have led to a view of abduction as being some hairy, difficult stuff, far too inefficient for any realistic applications. In this talk, we demonstrate how a fairly powerful version of abductive reasoning can be exercised through a direct use of Prolog, using its extension by Constraint Handling Rules as the engine to take care of abducible hypotheses.