The Experts below are selected from a list of 321 Experts worldwide ranked by ideXlab platform

Younes Bennani - One of the best experts on this subject based on the ideXlab platform.

  • predictive Connectionist Approach for vod bandwidth management
    Computer Communications, 2007
    Co-Authors: Danielo G Gomes, Younes Bennani, Nazim Agoulmine, Neuman J De Souza
    Abstract:

    This paper describes a step-by-step improvement process of a predictive Connectionist module applied in the context of Video on Demand Service Providers (VDSP) applications. The aim at the end is to provide a methodology based on estimation to right size bandwidth usage. The improvement methodology [G. Gomes, Un Modele Connexioniste pour la Prediction e l'Optimization de la Bande Passante: Approche Basee sur la Nature Autosimulaire du Trafic Video IP, doctorat thesis presented at Universite d'Evry - Val d'Essonne, France (2004)] consists of three phases named examples-based level, modular solution and HVS (Heuristic for Variable Selection) [Y. Bennani, M. Yacoub, Features selection and architecture optimization in Connectionist systems, International Journal of Neural Systems 10(5) (2000) 379-395]. In the first phase the ''sliding and overlaying'' technique is used for enabling the Predictive Connectionist Module (PCM) to be aware of dynamic input. In the second phase a new Connectionist network is added to the first one so that the proactive function with prediction could be achieved through a modular architecture. Finally, the HVS method is used in the third phase for identifying optimized Connectionist models with higher accuracy. Simulations results are provided which cover learning, prediction and evaluation phases.

  • AICCSA - Connectionist Approach for Website visitors behaviors mining
    Proceedings ACS IEEE International Conference on Computer Systems and Applications, 2001
    Co-Authors: Khalid Benabdeslem, Younes Bennani, Eric Janvier
    Abstract:

    Proposes a new version of the "topological maps" algorithm, which has been used to cluster Web site visitors. These are characterized by partially redundant variables over time. In this version, we only consider those input vectors' neurons that participate in the selection of the winning neuron in the map. In order to identify these neurons, we use a binary function. Subsequently, we apply a partial modification on the weights that relates them to the winning neuron. Using this new version, we obtained a clustering of Web site visitors' behaviors, which has been difficult to analyse before. This clustering allows a recommendation system to satisfy the Web site visitors' needs based on their cluster membership at each step in time.

  • Multi-expert and hybrid Connectionist Approach for pattern recognition: speaker identification task.
    International journal of neural systems, 1994
    Co-Authors: Younes Bennani
    Abstract:

    This paper presents and evaluates a modular/hybrid Connectionist system for speaker identification. Modularity has emerged as a powerful technique for reducing the complexity of Connectionist systems, allowing a priori knowledge to be incorporated into their design. In problems where training data are scarce, such modular systems are likely to generalize significantly better than a monolithic Connectionist system. In addition, modules are not restricted to be Connectionist: hybrid systems, with e.g. Hidden Markov Models (HMMs), can be designed, combining the advantages of Connectionist and non-Connectionist Approaches. Text independent speaker identification is an inherently complex task where the amount of training data is often limited. It thus provides an ideal domain to test the validity of the modular/hybrid Connectionist Approach. An architecture is developed in this paper which achieves this identification, based upon the cooperation of several Connectionist modules, together with an HMM module. When tested on a population of 102 speakers extracted from the DARPA-TIMIT database, perfect identification was obtained. Overall, our recognition results are among the best for any text-independent speaker identification system handling this population size. In a specific comparison with a system based on multivariate auto-regressive models, the modular/hybrid Connectionist Approach was found to be significantly better in terms of both accuracy and speed. Our design also allows for easy incorporation of new speakers.

  • ICASSP - A Connectionist Approach for automatic speaker identification
    International Conference on Acoustics Speech and Signal Processing, 1
    Co-Authors: Younes Bennani, Fogelman F Soulie, Patrick Gallinari
    Abstract:

    A Connectionist Approach to automatic speaker identification based on the learning vector quantization (VQ) algorithm is presented. For each adherent to the identification system, a number of references is fixed. The algorithm is based on a nearest-neighbor principle, with adaptation through learning. The identification is realized by comparing to a given threshold the distance of the unknown utterance to the nearest reference. Preliminary tests run on a ten-speaker set show an identification rate of 97% for MFC coefficients. The identification system and database used and the results obtained for different combinations of parameters are given. The system is evaluated by comparing its performances with a Bayesian system. >

Patrick Gallinari - One of the best experts on this subject based on the ideXlab platform.

  • Conceptual Clustering Using a Connectionist Approach
    ICANN ’93, 1993
    Co-Authors: Adélaïde Stévenin, Patrick Gallinari
    Abstract:

    We describe a Connectionist system for natural language processing in database query applications. It is a production system for conceptual decoding of task specific information and concept prediction. It has been designed for extracting semantic knowledge from text input. The system has been validated on an Air Travel Information System decoding task. It offers good performances with only a small number of parameters. Predicted concepts may be used as an intermediate step in a speech understanding system.

  • ICASSP - A Connectionist Approach for automatic speaker identification
    International Conference on Acoustics Speech and Signal Processing, 1
    Co-Authors: Younes Bennani, Fogelman F Soulie, Patrick Gallinari
    Abstract:

    A Connectionist Approach to automatic speaker identification based on the learning vector quantization (VQ) algorithm is presented. For each adherent to the identification system, a number of references is fixed. The algorithm is based on a nearest-neighbor principle, with adaptation through learning. The identification is realized by comparing to a given threshold the distance of the unknown utterance to the nearest reference. Preliminary tests run on a ten-speaker set show an identification rate of 97% for MFC coefficients. The identification system and database used and the results obtained for different combinations of parameters are given. The system is evaluated by comparing its performances with a Bayesian system. >

Kemal Oflazer - One of the best experts on this subject based on the ideXlab platform.

  • Solving Tangram puzzles: A Connectionist Approach
    International Journal of Intelligent Systems, 1993
    Co-Authors: Kemal Oflazer
    Abstract:

    We present a Connectionist Approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One Connectionist Approach models Tangram pieces and their possible placements and orientations as Connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral inhibitory connections from competing or conflicting units. the network of these Connectionist units, operating as a Boltzmann Machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. We present results from an implementation of our model using the Rochester Connectionist Simulator. © 1993 John Wiley & Sons, Inc.

  • A Connectionist Approach to Solving Tangram Puzzles
    Artificial Neural Networks, 1992
    Co-Authors: Kemal Oflazer
    Abstract:

    Publisher Summary This chapter presents a Connectionist Approach for solving Tangram puzzles, where the object is to decompose a given figure into seven basic geometric figures. The Approach models Tangram pieces and their possible placements and orientations as Connectionist units that receive excitatory connections from input units defining the puzzle and inhibitory connections from competing or conflicting units. The network of these units operating as a Boltzmann machine, relaxes into a configuration in which units defining the solution receive no inhibitory input from other units. The chapter presents the results that suggest that the Boltzmann machine Approach is applicable in domains with hard constraints.

Claudio Castellanos Sánchez - One of the best experts on this subject based on the ideXlab platform.

  • A bio-inspired Connectionist Approach for motion description through sequences of images
    Lecture Notes in Computer Science, 2007
    Co-Authors: Claudio Castellanos Sánchez
    Abstract:

    This paper presents a bio-inspired Connectionist Approach for motion description through sequences of images. First, this Approach is based on the architecture of oriented columns and the strong local and distributed interactions of the neurons in the primary visual cortex (V1). Secondly, in the integration and combination of their responses in the middle temporal area (MT). I propose an architecture in two layers : a causal spatio-temporal filtering (CSTF) of Gabor-like type which captures the oriented contrast and a mechanism of antagonist inhibitions (MAI) which estimates the motion. The first layer estimates the local orientation and speed, the second layer classifies the motion (global response) and both describe the motion and the pursuit trajectory. This architecture has been evaluated on sequences of natural and synthetic images.

  • A Connectionist Approach for visual perception of motion
    2004
    Co-Authors: Claudio Castellanos Sánchez, Bernard Girau, Frédéric Alexandre
    Abstract:

    Modeling visual perception of motion by Connectionist networks offers various areas of research for the development of real-time models of dynamic perception-action. In this paper we present the bases of a bio-inspired Connectionist Approach that is part of our development of neural networks applied to autonomous robotics. Our model of visual perception of motion is based on a causal adaptation of spatiotemporal Gabor lters. We use our causal spatiotemporal lters within a modular and strongly localized architecture that performs a shunting inhibition mechanism. This model has been evaluated on arti cial as well as natural image sequences. || La modélisation de la perception visuelle du mouvement par des réseaux connexionnists offre différents aires de recherche pour le développement en temps réel de modèles pour la dynamique perception action. Dans cet article nous présentons les fundaments d

G.p. Babu - One of the best experts on this subject based on the ideXlab platform.

  • A stochastic Connectionist Approach for global optimization with application to pattern clustering
    IEEE transactions on systems man and cybernetics. Part B Cybernetics : a publication of the IEEE Systems Man and Cybernetics Society, 2000
    Co-Authors: G.p. Babu, N.m. Murty, S. Sathiya Keerthi
    Abstract:

    In this paper, a stochastic Connectionist Approach is proposed for solving function optimization problems with real-valued parameters. With the assumption of increased processing capability of a node in the Connectionist network, we show how a broader class of problems can be solved. As the proposed Approach is a stochastic search technique, it avoids getting stuck in local optima. Robustness of the Approach is demonstrated on several multi-modal functions with different numbers of variables. Optimization of a well-known partitional clustering criterion, the squared-error criterion (SEC), is formulated as a function optimization problem and is solved using the proposed Approach. This Approach is used to cluster selected data sets and the results obtained are compared with that of the K-means algorithm and a simulated annealing (SA) Approach. The amenability of the Connectionist Approach to parallelization enables effective use of parallel hardware.

  • Connectionist Approach for clustering
    Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), 1
    Co-Authors: G.p. Babu, M.n. Murty
    Abstract:

    This paper presents a stochastic Connectionist Approach for cluster analysis. Clustering problem is formulated as a real-parameter function optimization problem and is solved using the proposed Approach. As the proposed Connectionist Approach performs stochastic search, it avoids getting stuck in a local minimum, and guarantees asymptotic convergence to optimal solution. The amenability of Connectionist Approaches to massive parallelization enables one to obtain linear speedup with available parallel hardware. Several data sets are clustered using the proposed Approach and the partitions obtained are (near) optimal in nature. Results pertaining to some important data sets are presented. >

  • Connectionist Approach for global optimization
    Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), 1
    Co-Authors: G.p. Babu, M.n. Murty
    Abstract:

    A Connectionist Approach for global optimization is proposed. The standard function set is tested. Results obtained, in the case of large scale problems, indicate excellent scalability of the proposed Approach. >