Search

Your search keyword '"Mouraud, Anthony"' showing total 12 results
Start Over Author "Mouraud, Anthony" Search Limiters Full Text
12 results on '"Mouraud, Anthony"'

3. Learning and discrimination through STDP in a top-down modulated associative memory

Author

Mouraud, Anthony and Paugam-Moisy, Hélène

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Artificial Intelligence
Abstract

This article underlines the learning and discrimination capabilities of a model of associative memory based on artificial networks of spiking neurons. Inspired from neuropsychology and neurobiology, the model implements top-down modulations, as in neocortical layer V pyramidal neurons, with a learning rule based on synaptic plasticity (STDP), for performing a multimodal association learning task. A temporal correlation method of analysis proves the ability of the model to associate specific activity patterns to different samples of stimulation. Even in the absence of initial learning and with continuously varying weights, the activity patterns become stable enough for discrimination.

Published
2006

4. DAMNED: A Distributed and Multithreaded Neural Event-Driven simulation framework

Author

Mouraud, Anthony, Puzenat, Didier, and Paugam-Moisy, Hélène

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Learning
Abstract

In a Spiking Neural Networks (SNN), spike emissions are sparsely and irregularly distributed both in time and in the network architecture. Since a current feature of SNNs is a low average activity, efficient implementations of SNNs are usually based on an Event-Driven Simulation (EDS). On the other hand, simulations of large scale neural networks can take advantage of distributing the neurons on a set of processors (either workstation cluster or parallel computer). This article presents DAMNED, a large scale SNN simulation framework able to gather the benefits of EDS and parallel computing. Two levels of parallelism are combined: Distributed mapping of the neural topology, at the network level, and local multithreaded allocation of resources for simultaneous processing of events, at the neuron level. Based on the causality of events, a distributed solution is proposed for solving the complex problem of scheduling without synchronization barrier., Comment: 6 pages

Published
2005

5. Four MPC implementations compared on the Quadruple Tank Process Benchmark: pros and cons of neural MPC*

Author

Clément Blaud, Pierre, Chevrel, Philippe, Claveau, Fabien, Haurant, Pierrick, Mouraud, Anthony, CEA Tech Pays-de-la-Loire (DP2L), CEA Tech en régions (CEA-TECH-Reg), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Département Automatique, Productique et Informatique (IMT Atlantique - DAPI), IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Commande, Observation, Diagnostic et Expérimentation (LS2N - équipe CODEx), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Nantes Université (Nantes Univ), Département Systèmes Energétiques et Environnement (IMT Atlantique - DSEE), Optimisation - Système - Energie (GEPEA-OSE), Laboratoire de génie des procédés - environnement - agroalimentaire (GEPEA), École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique (ONIRIS)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - Institut Universitaire de Technologie Saint-Nazaire (Nantes Univ - IUT Saint-Nazaire), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique (ONIRIS)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), and Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)

Subjects
Artificial neural network, Control and Systems Engineering, [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, Model predictive control, ComputingMilieux_MISCELLANEOUS, Quadruple tank process
Abstract

International audience; This study aims to aid understanding of Model Predictive Control (MPC) alternatives through comparing most interesting MPC implementations. This comparison will be performed intrinsically and illustrated using the four-tank benchmark, widely studied by academics taking care of industrial perspectives. Although MPC provides advanced control solutions for a wide class of dynamical systems, challenges arise in managing the compromise between accuracy, computational cost and resilience, depending on the type of model used. In this study, linear, linear time-varying and non-linear MPCs are compared to MPC that uses a neural network based predictive model identified from data. The tuning and implementation methods considered are discussed, and accurate simulation results provided and analyzed. Precisely, the performance of each method (linear, linear time-varying, non-linear MPC) are compared to the neural MPC. Pros and cons of neural MPC are highlighted.

Published
2022

6. ResNet and PolyNet based identification and (MPC) control of dynamical systems: a promising way

Author

Blaud, Pierre Clement, Chevrel, Philippe, Claveau, Fabien, Haurant, Pierrick, Mouraud, Anthony, CEA Tech Pays-de-la-Loire (DP2L), CEA Tech en régions (CEA-TECH-Reg), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commande, Observation, Diagnostic et Expérimentation (LS2N - équipe CODEx), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Nantes Université (Nantes Univ), Département Automatique, Productique et Informatique (IMT Atlantique - DAPI), IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Optimisation - Système - Energie (GEPEA-OSE), Laboratoire de génie des procédés - environnement - agroalimentaire (GEPEA), École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique (ONIRIS)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - Institut Universitaire de Technologie Saint-Nazaire (Nantes Univ - IUT Saint-Nazaire), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique (ONIRIS)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ), and Département Systèmes Energétiques et Environnement (IMT Atlantique - DSEE)

Subjects
PolyNet, [SPI]Engineering Sciences [physics], Artificial neural networks, model predictive control, quadruple tank process, [INFO.INFO-RO]Computer Science [cs]/Operations Research [cs.RO], [MATH]Mathematics [math], feedforward neural networks, ResNet
Abstract

International audience; This paper deals with model predictive control synthesis which take benefits from artificialneural networks to model (non-linear) dynamical system. More precisely, thanks to a systematic andrigorous methodology, it is shown that residual networks (ResNet) and PolyInception networks (PolyNet)neural network architectures, developed initially for image recognition, are very good candidate for i)identification of dynamical systems, ii) being used as embedded model in a model predictive control laws.Concretely, the widely used non-linear dynamical system quadruple tank process is used as a benchmark.The neural network architectures studied are i) feedforward networks as a reference point, and the two otherlinked to Euler integration method ii) residual networks and iii) PolyInception networks. Networks trainingis performed by mixing classical back-propagation algorithm and hyperparameters optimisation throughheuristics. The identification results provided show that neural networks of types ii) and iii) perform betterthan the classical one i), with a better generalisation capability. Finally, model predictive controllers aresynthesized based on the various networks trained. The simulation results obtained for controlling waterlevels of a 4 tanks system benchmark give interesting insights. They show that residual networks basedmodel predictive control is better suited than feedforward networks and PolyInception networks based ones,both taking into account computation time and set point errors.

Published
2022

10. DAMNED: A Distributed and Multithreaded Neural Event-Driven simulation framework

Author

Mouraud, Anthony, Puzenat, Didier, Paugam-Moisy, Hélène, Groupe de Recherche en Informatique et Mathématiques Appliquées Antilles-Guyane (GRIMAAG), Université des Antilles et de la Guyane (UAG), Institut des Sciences Cognitives (ISC), Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Université de Lyon

Subjects
FOS: Computer and information sciences, Quantitative Biology::Neurons and Cognition, Scheduling, Computer Science::Neural and Evolutionary Computation, Computer Science - Neural and Evolutionary Computing, [SCCO.COMP]Cognitive science/Computer science, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Machine Learning (cs.LG), Spiking Neural Networks, Computer Science - Learning, Multi-threading, Parallel Computing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Event-Driven Simulations, Neural and Evolutionary Computing (cs.NE), [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]
Abstract

In a Spiking Neural Networks (SNN), spike emissions are sparsely and irregularly distributed both in time and in the network architecture. Since a current feature of SNNs is a low average activity, efficient implementations of SNNs are usually based on an Event-Driven Simulation (EDS). On the other hand, simulations of large scale neural networks can take advantage of distributing the neurons on a set of processors (either workstation cluster or parallel computer). This article presents DAMNED, a large scale SNN simulation framework able to gather the benefits of EDS and parallel computing. Two levels of parallelism are combined: Distributed mapping of the neural topology, at the network level, and local multithreaded allocation of resources for simultaneous processing of events, at the neuron level. Based on the causality of events, a distributed solution is proposed for solving the complex problem of scheduling without synchronization barrier., Comment: 6 pages

Published
2006

12. Simple spatio-temporal transformation with subthreshold integration in the saccadic system.

Author

Daucé, Emmanuel, Mouraud, Anthony, and Guillaume, Alain

Subjects
*SACCADIC eye movements
Abstract

An abstract is presented of the research paper "Simple spatio-temporal transformation with subthreshold integration in the saccadic system," by Anthony Mouraud and colleagues, which was presented at the Twentieth Annual Computational Neuroscience Meeting held in Sweden in July 2011.

Published
2011
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results