Search

Your search keyword '"Hervé Frezza-Buet"' showing total 48 results
Start Over Author "Hervé Frezza-Buet"
48 results on '"Hervé Frezza-Buet"'

31. Sample-efficient batch reinforcement learning for dialogue management optimization

Author

Matthieu Geist, Hervé Frezza-Buet, Senthilkumar Chandramohan, Olivier Pietquin, SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Georgia Tech Lorraine [Metz], Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-Georgia Institute of Technology [Atlanta]-CentraleSupélec-Ecole Nationale Supérieure des Arts et Metiers Metz-Centre National de la Recherche Scientifique (CNRS), Ecole Nationale Supérieure des Arts et Metiers Metz-Georgia Institute of Technology [Atlanta]-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), and Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)

Subjects
Computer science, business.industry, User modeling, 020206 networking & telecommunications, Sample (statistics), 02 engineering and technology, Machine learning, computer.software_genre, Task (project management), Dynamic programming, Computational Mathematics, Bellman equation, 0202 electrical engineering, electronic engineering, information engineering, Computer Science (miscellaneous), Reinforcement learning, 020201 artificial intelligence & image processing, Artificial intelligence, Set (psychology), business, computer, Natural language
Abstract

Spoken Dialogue Systems (SDS) are systems which have the ability to interact with human beings using natural language as the medium of interaction. A dialogue policy plays a crucial role in determining the functioning of the dialogue management module. Handcrafting the dialogue policy is not always an option, considering the complexity of the dialogue task and the stochastic behavior of users. In recent years approaches based on Reinforcement Learning (RL) for policy optimization in dialogue management have been proved to be an efficient approach for dialogue policy optimization. Yet most of the conventional RL algorithms are data intensive and demand techniques such as user simulation. Doing so, additional modeling errors are likely to occur. This paper explores the possibility of using a set of approximate dynamic programming algorithms for policy optimization in SDS. Moreover, these algorithms are combined to a method for learning a sparse representation of the value function. Experimental results show that these algorithms when applied to dialogue management optimization are particularly sample efficient , since they learn from few hundreds of dialogue examples. These algorithms learn in an off-policy manner, meaning that they can learn optimal policies with dialogue examples generated with a quite simple strategy. Thus they can learn good dialogue policies directly from data , avoiding user modeling errors.

Published
2011
Full Text
View/download PDF

32. Dynamic Neural Field Optimization using the Unscented Kalman Filter

Author

Matthieu Geist, Jérémy Fix, Olivier Pietquin, Hervé Frezza-Buet, Georgia Tech Lorraine [Metz], Ecole Nationale Supérieure des Arts et Metiers Metz-Georgia Institute of Technology [Atlanta]-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC), SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Université de Franche-Comté (UFC), and Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-Georgia Institute of Technology [Atlanta]-CentraleSupélec-Ecole Nationale Supérieure des Arts et Metiers Metz-Centre National de la Recherche Scientifique (CNRS)

Subjects
Artificial neural network, Noise (signal processing), Computer science, Estimation theory, Continuous modelling, 02 engineering and technology, Function (mathematics), Kalman filter, computer.software_genre, Expert system, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Control theory, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Gradient descent, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery
Abstract

International audience; Dynamic neural fields have been proposed as a continuous model of a neural tissue. When dynamic neural fields are used in practical applications, the tuning of their parameters is a challenging issue that most of the time relies on expert knowledge on the influence of each parameter. The methods that have been proposed so far for automatically tuning these parameters rely either on genetic algorithms or on gradient descent. The second category of methods requires to explicitly compute the gradient of a cost function which is not always possible or at least difficult and costly. Here we propose to use unscented Kalman filters, a derivative-free algorithm for parameter estimation, which reveals to efficiently optimize the parameters of a dynamic neural field.

Published
2011
Full Text
View/download PDF

33. Can Self-Organization Emerge through Dynamic Neural Fields Computation?

Author

Frédéric Alexandre, Lucian Alecu, Hervé Frezza-Buet, SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer science, Computation, [SCCO.COMP]Cognitive science/Computer science, Neural fields, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Field (computer science), 03 medical and health sciences, 0302 clinical medicine, Self organisation, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, cognitive systems, Layer (object-oriented design), Flexibility (engineering), Self-organization, Quantitative Biology::Neurons and Cognition, business.industry, Perspective (graphical), self-organization, Human-Computer Interaction, 020201 artificial intelligence & image processing, dynamic neural fields, Artificial intelligence, business, 030217 neurology & neurosurgery, Software
Abstract

International audience; In this paper, dynamic neural fields are used to develop key features of a cortically-inspired computational module. Under the perspective of designing computational systems that can exhibit the flexibility and genericity of the cortical substrate, using neural field as the competition layer for self-organizing modules has to be considered. However, despite the fact that they serve as a biologically-inspired model, applying dynamic neural fields to drive self-organization is not straightforward. In order to address that issue, an original method for evaluating neural field equations is proposed, based on statistical measurements of the field behavior in some scenarios. Limitations of classical neural field equations are then quantified, and an original field equation is proposed to overcome these difficulties. The performance of the proposed field model is discussed in comparison with some previously considered models, leading to the promotion of the proposed model as a suitable mean for processing competition in cortex-like computation for cognitive systems.

Published
2011
Full Text
View/download PDF

34. An Interactive Problem Modeller and PDE Solver, Distributed on Large Scale Architectures

Author

Nicolas Fressengeas, Hervé Frezza-Buet, Jens Gustedt, Stéphane Vialle, Laboratoire Matériaux Optiques, Photonique et Systèmes (LMOPS), CentraleSupélec-Université de Lorraine (UL), SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Algorithms for the Grid (ALGORILLE), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), CPER Région Lorrain MIS - InterCell, Grid'5000, and Gustedt, Jens

Subjects
ComputingMethodologies_SYMBOLICANDALGEBRAICMANIPULATION, [INFO.INFO-DC] Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], MathematicsofComputing_NUMERICALANALYSIS, [MATH.MATH-AP]Mathematics [math]/Analysis of PDEs [math.AP], [MATH.MATH-AP] Mathematics [math]/Analysis of PDEs [math.AP], [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]
Abstract

http://lifc.univ-fcomte.fr/dfma07/; International audience; This paper introduces a research project and a software environment to speed up and size up problem modeling with Partial Differential Equations (PDE). These PDE are defined from a \Mathematica interface, and are automatically solved by a devoted cellular automata program generated to be run on mainframes, clusters and Grids. Moreover, an interactive and graphic control of the cellular automata running allows to analyze the PDE model relevance. This environment improves large scale simulation usage in early stages of research projects.

Published
2007

35. Making competition in neural fields suitable for computational architectures

Author

Olivier Ménard, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Wlodzislaw Duch and Janusz Kacprzyk and Erkki Oja and Slawomir Zadrozny

Subjects
Spiking neural network, Physical neural network, Artificial neural network, Quantitative Biology::Neurons and Cognition, business.industry, Computer science, 05 social sciences, Computer Science::Neural and Evolutionary Computation, Neural fields, continuum neural field theory, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 050105 experimental psychology, Models of neural computation, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Unsupervised learning, 020201 artificial intelligence & image processing, 0501 psychology and cognitive sciences, Artificial intelligence, business
Abstract

In this paper, a new competition mechanism for neural fields is proposed, as well as first experimental studies of its robustness. The computational properties of this algorithm are discussed, arguing that such properties are suitable for neural architectures, where some restrictions of the usual neural fields competition methods are not acceptable.

Published
2005
Full Text
View/download PDF

36. Coherent learning in cortical maps: A generic approach

Author

O. Menard, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Process (engineering), Computer science, business.industry, 02 engineering and technology, Neurophysiology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Cortex (botany), 03 medical and health sciences, 0302 clinical medicine, 0202 electrical engineering, electronic engineering, information engineering, Robot, 020201 artificial intelligence & image processing, Artificial intelligence, business, continuum neural field theory self-organizing maps multi-modal, 030217 neurology & neurosurgery
Abstract

This paper presents a computational model inspired from the cortex organization that defines coherent learning in multiple cortical maps, in order to perform multi-modal coordination. The joint self-organization of the maps is described as a process allowing dealing with multi-modal information within cooperative distributed modules. The very purpose of this approach is the design of a generic distributed architecture for robotic servo-control from a functional view of the cortical information processing.

Published
2005

37. From Natural to Artificial Intelligence: Numerical processing for cognitive tasks

Author

Hervé Frezza-Buet, Frédéric Alexandre, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Paul Bourgine and Jean-Pierre Nadal

Subjects
Cognitive model, cognition, Elementary cognitive task, renforcement, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], 02 engineering and technology, Machine learning, computer.software_genre, 050105 experimental psychology, Knowledge integration, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, Associative property, reinforcement, Artificial neural network, business.industry, économie, 05 social sciences, Cognition, economics, Modular design, approche évolutionnaire, evolutionary approach, Unsupervised learning, 020201 artificial intelligence & image processing, Artificial intelligence, business, Psychology, computer, artificial neural networks, réseaux de neurones artificiels
Abstract

Contribution à un ouvrage.; Cognitive modeling can be derived from expert knowledge integration or experimental data analysis. This chapter introduces these two main ways of modeling and concentrates on the latter aspect and the related numerical tools together with their possible role. More precisely, the evolutionary approach is presented for optimization and tuning, artificial neural networks for associative reasoning and the stochastic approach for planning. We then conclude on the need for a modular framework, integrating these numerical and other symbolic tools.

Published
2004

38. Multi-map self-organization for sensorimotor learning: a cortical approach

Author

Olivier Ménard, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and IEEE

Subjects
Computer science, self-organisation, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], 02 engineering and technology, Sensorimotor learning, Machine learning, computer.software_genre, résonance, 03 medical and health sciences, 0302 clinical medicine, Connectionism, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, connectionism, Self-organization, Robot kinematics, connexionnisme, Artificial neural network, business.industry, auto-organisation, sensorimotor application, application sensori-motrice, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, 030217 neurology & neurosurgery
Abstract

Colloque avec actes et comité de lecture. internationale.; International audience; We present a cortically-inspired self-organizing model designed to deal with sensory-motor applications, and very first experimental results. This model contains several maps and produces resonance effects between these maps in order to reach an organization compromise.

Published
2003

39. From a biological to a computational model for the autonomous behavior of an animat

Author

Frédéric Alexandre, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Information Systems and Management, Computer science, biologically inspired model, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], cortical column, 02 engineering and technology, 050105 experimental psychology, Theoretical Computer Science, Domain (software engineering), Animat, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, 0501 psychology and cognitive sciences, connectionism, Set (psychology), connexionnisme, business.industry, 05 social sciences, Computer Science Applications, Automaton, colonne corticale, cortex, Control and Systems Engineering, Robot, 020201 artificial intelligence & image processing, Artificial intelligence, modèle d'inspiration biologique, Autonomous system (mathematics), business, artificial neural networks, réseaux de neurones artificiels, Software
Abstract

Endowing an autonomous system like a robot with intelligent behavior is a difficult problem for several reasons. First, behavior is such a wide topic that a general framework paradigm of inspiration must be chosen in order to obtain a consistent model. Such a framework can be for example biological modeling or an artificial intelligence approach. Second, a general framework is not sufficient to determine a fully specified program to be implemented in a robot. Many choices, tuning and tests must be carried out before obtaining a robust system. This paper describes this. First, a biological model is presented, based on the definition of cortex-like automata, representing elementary functions in the perceptive, motor or associative domain. These automata are connected in a network whose architecture, functioning and learning rules are described in a cortical framework. Second, the computational model derived from that biological model is specified. The way units exchange and compute variables through links is explained, with reference to corresponding biological elements. It is then easier to report experiments allowing an autonomous system to learn regularities of a simple environment and to exploit them to satisfy some internal drives. Even if additional biological hints can be added, this model allow us to better understand how a biological model can be implemented and how biological properties can emerge from a distributed set of units.

Published
2002
Full Text
View/download PDF

41. Integration of Biologically Inspired Temporal Mechanisms into a Cortical Framework for Sequence Processing

Author

Frédéric Alexandre, Nicolas Rougier, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP), none, and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Dynamic time warping, traitement de séquences, Computer science, media_common.quotation_subject, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], connexionism, 02 engineering and technology, temporal mechanisms, 03 medical and health sciences, 0302 clinical medicine, Connectionism, sequence processing, Perception, Learning rule, 0202 electrical engineering, electronic engineering, information engineering, Pattern matching, Dimension (data warehouse), media_common, Data processing, business.industry, Task (computing), cortex, connectionnisme, 020201 artificial intelligence & image processing, Artificial intelligence, business, mécanismes temporels, 030217 neurology & neurosurgery
Abstract

Contribution à un ouvrage.; Whereas classical connectionist models can hardly cope with difficult dynamic tasks with a strong temporal factor, many temporal mechanisms inspired with neurobiological data has been proposed in the past and yield efficient time processing properties. The goal of this chapter is to show that, beyond these isolated mechanisms, their integration in a more general architectural and functional framework can potentiate their power and make them usable for non trivial behavioral tasks. We propose a cerebral framework, from the neuronal to the behavioral level, and give some applicative illustrations that underline the encouraging results obtained today.

Published
2000

42. Neuronal mechanisms for sequence learning in behavioral modeling

Author

Nicolas P. Rougier, Hervé Frezza-Buet, Frédéric Alexandre, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
associatif, sequence learning, apprentissage séquence, cortex, hippocampus, hippocampe, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], associative, frontal
Abstract

Colloque avec actes et comité de lecture.; Sequence learning and management have been reported as central features in behavioral studies. Indeed, tasks like route memorization or planning are temporal behaviors and can be hardly modeled without taking the temporal aspect into consideration. On the contrary, classical information processing tools are not very efficient at such temporal processing. In this paper, we shortly review these tools and show that another approach, close to neurobiological modeling, can yield a variety of neuronal mechanisms for several aspects of sequence learning and management.

Published
1999

43. Modeling prefrontal functions for robot navigation

Author

Frédéric Alexandre, Hervé Frezza-Buet, Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), and Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique de Lorraine (INPL)-Université Nancy 2-Université Henri Poincaré - Nancy 1 (UHP)

Subjects
0303 health sciences, Quantitative Biology::Neurons and Cognition, Goal orientation, Computer science, business.industry, frontal cortex, neural planning, [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH], Mobile robot, Computer Science::Robotics, 03 medical and health sciences, planification neuronale, 0302 clinical medicine, medicine.anatomical_structure, Action (philosophy), cortex frontal, Cortex (anatomy), medicine, Robot, Artificial intelligence, Motion planning, Prefrontal cortex, business, 030217 neurology & neurosurgery, 030304 developmental biology
Abstract

Colloque avec actes et comité de lecture.; This paper presents a model of cooperation between representations of correlation in the associative cortex and goal oriented representations of action in the prefrontal cortex. The model is applied to robot navigation and gives a framework for addressing planning with numerical neural techniques.

Published
1999

44. Reconstruction d'état caché avec cartes auto-organisatrices récurrentes

Author

Alain Dutech, Jeremy Fix, Hervé Frezza-Buet, Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria), Bio-Inspired, Situated and Cellular Unconventional Information Technologies (BISCUIT), Department of Complex Systems, Artificial Intelligence & Robotics (LORIA - AIS), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria), CentraleSupélec, Buffet, Olivier, Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Reconstruction d'état, Cartes auto-organisatrices, Chaînes de Markov cachées, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

National audience; Quand les ´etats d’un processus ne sont pas Markoviens(POMDP par exemple), la convergencedes algorithmes d’apprentissage par renforcementn’est pas garantie. Une solution est de reconstruireun processus Markovien en partant dela s´equence des ´etats. Dans ce but, nous exploronsles capacit´es d’architectures r´ecurrentesqui s’appuient sur des cartes neuronales autoorganisatricespour apprendre `a pr´edire dess´equences d’observations issues de HMM.

45. InterCell: a Software Suite for Rapid Prototyping and Parallel Execution of Fine Grained Applications

Author

Jens Gustedt, Stéphane Vialle, Hervé Frezza-Buet, Havh Boumba Sitou, D., Nicolas Fressengeas, Algorithms for the Grid (ALGORILLE), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Laboratoire Matériaux Optiques, Photonique et Systèmes (LMOPS), CentraleSupélec-Université de Lorraine (UL), and Van Luchene, Sébastien

Subjects
interactivity, fine grained parallel models, [INFO.INFO-DC] Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], rapid prototyping
Abstract

International audience; InterCell is an open, operational software suite for implementation, code generation and interactive simulation of fine grained parallel computational models. This article describes the software architecture, some use cases from physics and cortical networks as well as first performance measurements.

46. Cellular based simulation of semiconductors thin films

Author

Havh Boumba Sitou, D., Sidi Ould Saad Hamady, Nicolas Fressengeas, Hervé Frezza-Buet, Stéphane Vialle, Jens Gustedt, Patrick Mercier, Laboratoire Matériaux Optiques, Photonique et Systèmes (LMOPS), CentraleSupélec-Université de Lorraine (UL), SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Neuromimetic intelligence (CORTEX), INRIA Lorraine, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), Algorithms for the Grid (ALGORILLE), and Fressengeas, Nicolas

Subjects
[PHYS.PHYS.PHYS-OPTICS] Physics [physics]/Physics [physics]/Optics [physics.optics], [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics]

47. Online Speaker Diarization with a Size-Monitored Growing Neural Gas Algorithm

Author

Jean-Louis GUTZWILLER, Hervé Frezza-Buet, Olivier Pietquin, Van Luchene, Sébastien, Michel Verleysen, SUPELEC-Campus Metz, and Ecole Supérieure d'Electricité - SUPELEC (FRANCE)

Abstract

International audience; This paper proposes a method for segmenting and clustering an audio flow on the basis of speaker turns. This process, also known as speaker diarization, is of major importance in multimedia indexation. Here, we propose to realize this process online and without any prior knowledge on the number of speakers. This is done thanks to a statistical modelling of speakers based on a size-monitored growing neural gas algorithm.

48. YARBUS : Yet Another Rule Based belief Update System Jérémy Fix Hervé Frezza-Buet

Author

Jeremy Fix, Hervé Frezza-Buet, Georgia Tech Lorraine [Metz], Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-Georgia Institute of Technology [Atlanta]-CentraleSupélec-Ecole Nationale Supérieure des Arts et Metiers Metz-Centre National de la Recherche Scientifique (CNRS), IMS : Information, Multimodalité & Signal, SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE)-Ecole Supérieure d'Electricité - SUPELEC (FRANCE), CentraleSupelec, and ANR-12-CORD-0021,MaRDi,Dialogue Homme-Robot(2012)

Subjects
InformationSystems_MODELSANDPRINCIPLES, InformationSystems_INFORMATIONINTERFACESANDPRESENTATION(e.g.,HCI), [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC]
Abstract

We introduce a new rule based system for belief tracking in dialog systems. Despite the simplicity of the rules being considered, the proposed belief tracker ranks favourably compared to the previous submissions on the second and third Dialog State Tracking challenges. The results of this simple tracker allows to reconsider the performances of previous submissions using more elaborate techniques.

Catalog

Books, media, physical & digital resources
See catalog results