Y Bennani | PubMed Health

PubMed2000

Features selection and architecture optimization in connectionist systems.

In this paper, we propose a features selection measure and an architecture optimization procedure for Multi-Layer Perceptrons (MLP). The algorithm presented in this contribution employs a heuristic measure named HVS (Heuristic for Variable Selection). This new measure allows us to identify and select important variables in the features space. This can be achieved by eliminating redundant features and those which do not contain enough relevant information. The proposed measure is used in a new procedure aimed at selecting the "best" MLP architecture given an initial structure. Application results for two generic problems: regression and discrimination, demonstrates the proposed selection algorithm's effectiveness in identifying optimized connectionist models with higher accuracy. Finally, an extension of HVS, named epsilonHVS, is proposed for discriminative features detection and architecture optimization for Time Delay Neural Networks models (TDNN).

Algorithms↗

PubMed1995

A modular and hybrid connectionist system for speaker identification.

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, and allowing a priori knowledge to be incorporated into their design. 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. To achieve such identification, we develop, in this paper, an architecture based upon the cooperation of several connectionist modules, and a Hidden Markov Model module. When tested on a population of 102 speakers extracted from the DARPA-TIMIT database, perfect identification was obtained.

Databases, Factual↗

PubMed1994

Multi-expert and hybrid connectionist approach for pattern recognition: speaker identification task.

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.

Artificial Intelligence↗

PubMed1992

[Segmental small intestine transplantation in dogs: comparison between a jejunal graft and an ileal graft].

The aim of this study was to compare segmental grafts of jejunum and ileum in a dog model. 14 segmental grafts, 8 ileal (Il. A) and 6 jejunal (Jej. A.), were successfully allografted as 120 cm-Thiry-Vella segments. Immunosuppressive therapy consisted of cyclosporin 25 mg/kg/day per os. Monitoring was performed by histology and absorption (maltose and xylose) studies as well as analysis of brush border enzymes. No cases of Graft-versus-host disease were observed. Six allografts (42.5 per cent) including 3 Jej. A. (50 per cent) and 3 Il. A. (37.5 per cent) were rejected during the first three months. Eight allografts (5 Il. A. and 3 Jej. A.) were tolerated for up to 3 months and were removed: 2 Il. A. and 2 Jej. A. were normal, while 2 Il. A. and one Jej. A presented with signs of chronic rejection and one Il. A. with advanced rejection. Jej. A. and Il. A. showed a similar course, by means of immunologic reactions as well as functional characteristics. It is concluded that there is no major difference between Jej. A. and Il. A. in the dog. Because of the specialized absorptive functions of the ileum and its adaptative properties, ileal segmental grafts should be preferred to jejunal grafts for the treatment of short-gut syndrome.

Alkaline Phosphatase↗