University Sétif 1 FERHAT ABBAS Faculty of Sciences
Résultat de la recherche
3 résultat(s) recherche sur le mot-clé 'Optimization'
Ajouter le résultat dans votre panier Affiner la recherche Générer le flux rss de la recherche
Partager le résultat de cette recherche
Titre : Artificial Rabbit Optimization For Tuning Deep Learning Parameters Type de document : texte imprimé Auteurs : Yasmine Tigha ; Ibtihel Boussahel ; Semcheddine,Moussa, Directeur de thèse Editeur : Setif:UFA Année de publication : 2023 Importance : 1 vol (84 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Optimization Artificial Rabbit Optimization Genetic Algorithms Particle
Swarm Optimization Grey Wolf Optimization Deep Learning learning rate and dropout rateIndex. décimale : 004 - Informatique Résumé : Deep learning models’ performance heavily relies on selecting appropriate hyperparameters,
such as learning rate, dropout rate , and network architecture.
However, finding the optimal values for these hyperparameters is challenging due
to the lack of fixed rules.
In this thesis, we propose using bio-inspired algorithms, including ARO, PSO,
GA, and GWO, to optimize the hyperparameters of a feed-forward neural network.
The experiments are conducted on the MNIST dataset, commonly used for image
analysis. Comparing the accuracy of models trained with these algorithms, with
and without dropout, reveals that bio-inspired algorithms improve deep learning
model accuracy. Incorporating bio-inspired algorithms in hyperparameter tuning
shows promise for optimizing deep learning models. By drawing inspiration from
nature, these algorithms enhance performance and generalization, demonstrating
their efficacy in deep learning hyperparameter tuning
Côte titre : MAI/0761 En ligne : https://drive.google.com/file/d/1WcfNow4t2G8wXoZTx2oNMTp_XM-CbHG0/view?usp=drive [...] Format de la ressource électronique : Artificial Rabbit Optimization For Tuning Deep Learning Parameters [texte imprimé] / Yasmine Tigha ; Ibtihel Boussahel ; Semcheddine,Moussa, Directeur de thèse . - [S.l.] : Setif:UFA, 2023 . - 1 vol (84 f .) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Optimization Artificial Rabbit Optimization Genetic Algorithms Particle
Swarm Optimization Grey Wolf Optimization Deep Learning learning rate and dropout rateIndex. décimale : 004 - Informatique Résumé : Deep learning models’ performance heavily relies on selecting appropriate hyperparameters,
such as learning rate, dropout rate , and network architecture.
However, finding the optimal values for these hyperparameters is challenging due
to the lack of fixed rules.
In this thesis, we propose using bio-inspired algorithms, including ARO, PSO,
GA, and GWO, to optimize the hyperparameters of a feed-forward neural network.
The experiments are conducted on the MNIST dataset, commonly used for image
analysis. Comparing the accuracy of models trained with these algorithms, with
and without dropout, reveals that bio-inspired algorithms improve deep learning
model accuracy. Incorporating bio-inspired algorithms in hyperparameter tuning
shows promise for optimizing deep learning models. By drawing inspiration from
nature, these algorithms enhance performance and generalization, demonstrating
their efficacy in deep learning hyperparameter tuning
Côte titre : MAI/0761 En ligne : https://drive.google.com/file/d/1WcfNow4t2G8wXoZTx2oNMTp_XM-CbHG0/view?usp=drive [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0761 MAI/0761 Mémoire Bibliothéque des sciences Anglais Disponible
DisponibleDesign and implementation of software platform for bioinspired optimization algorithms / Islam Bouabdallah
Titre : Design and implementation of software platform for bioinspired optimization algorithms Type de document : texte imprimé Auteurs : Islam Bouabdallah ; Hichem Badis ; Moussa Semchedine, Directeur de thèse Editeur : Setif:UFA Année de publication : 2023 Importance : 1 vol. (56 f.) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Optimization Bio-inspired algorithms benchmark functions Particle swarm optimization Firefly
algorithm Grey wolf optimization Whale optmization Artificial rabbit optimizationIndex. décimale : 004 Informatique Résumé : Bio-inspired algorithms have been widely used by scientists because of their ability to solve complex
problems efficiently. In this work, we present the design and implementation of a software platform for bioinspired
optimization algorithms.The platform provides a user-friendly interface for selecting and comparing
different algorithms, including genetic algorithms, particle swarm optimization, and more optimization algorithms.
We also provide a set of benchmark functions to test the performance of the implemented algorithms.The
platform is open source and available for researchers and practitioners in the field of optimization to facilitate
their utilization of these algorithms.Côte titre : MAI/0753 En ligne : https://drive.google.com/file/d/1v5kW5pct42yrVQFRBm8Dkzht5p2rGTjS/view?usp=drive [...] Format de la ressource électronique : Design and implementation of software platform for bioinspired optimization algorithms [texte imprimé] / Islam Bouabdallah ; Hichem Badis ; Moussa Semchedine, Directeur de thèse . - [S.l.] : Setif:UFA, 2023 . - 1 vol. (56 f.) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Optimization Bio-inspired algorithms benchmark functions Particle swarm optimization Firefly
algorithm Grey wolf optimization Whale optmization Artificial rabbit optimizationIndex. décimale : 004 Informatique Résumé : Bio-inspired algorithms have been widely used by scientists because of their ability to solve complex
problems efficiently. In this work, we present the design and implementation of a software platform for bioinspired
optimization algorithms.The platform provides a user-friendly interface for selecting and comparing
different algorithms, including genetic algorithms, particle swarm optimization, and more optimization algorithms.
We also provide a set of benchmark functions to test the performance of the implemented algorithms.The
platform is open source and available for researchers and practitioners in the field of optimization to facilitate
their utilization of these algorithms.Côte titre : MAI/0753 En ligne : https://drive.google.com/file/d/1v5kW5pct42yrVQFRBm8Dkzht5p2rGTjS/view?usp=drive [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0753 MAI/0753 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible
Titre : Task offloading, Scheduling and Resource Allocation Type de document : texte imprimé Auteurs : Maroua Rehahla ; Fatima Zohra Saadoune ; Djamila Mechta, Directeur de thèse Editeur : Setif:UFA Année de publication : 2023 Importance : 1 vol. (66 f.) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Internet of Things Edge Computing Task Scheduling Resource Allocation Optimization Index. décimale : 004 Informatique Résumé : Task offloading, scheduling and resource allocation are the main elements of edge computing.
This Master thesis aims to find a new technique to do the offloading, the task scheduling, and the resource
allocation, based on artificial intelligence (AI). we will talk about the main definitions, concepts, analyzes
and discusses some surveys and related works to offloading, task scheduling and resource allocation. Our
contribution is proposed a new hybrid method for task offloading and resource allocation based on artificial
intelligence (AI) especially the K-means algorithm (KMA) for the offloading decision and the genetic algorithm
(GA) for the scheduling and resources allocation. Finally, this method takes advantages of both the artificial
intelligence (k-means clustering) and genetic algorithm (GA) to optimize the makespan, the bandwidth and
the energy consumption. After comparing our work with authors works, we have found that our proposed is
we notice that the proposed algorithm is efficient in terms of makespan, bandwidth and energy consumptionCôte titre : MAI/0749 En ligne : https://drive.google.com/file/d/1RvsRQn9ecY65LzPjLco6gwyt0IDoU3uL/view?usp=drive [...] Format de la ressource électronique : Task offloading, Scheduling and Resource Allocation [texte imprimé] / Maroua Rehahla ; Fatima Zohra Saadoune ; Djamila Mechta, Directeur de thèse . - [S.l.] : Setif:UFA, 2023 . - 1 vol. (66 f.) ; 29 cm.
Langues : Français (fre)
Catégories : Thèses & Mémoires:Informatique Mots-clés : Internet of Things Edge Computing Task Scheduling Resource Allocation Optimization Index. décimale : 004 Informatique Résumé : Task offloading, scheduling and resource allocation are the main elements of edge computing.
This Master thesis aims to find a new technique to do the offloading, the task scheduling, and the resource
allocation, based on artificial intelligence (AI). we will talk about the main definitions, concepts, analyzes
and discusses some surveys and related works to offloading, task scheduling and resource allocation. Our
contribution is proposed a new hybrid method for task offloading and resource allocation based on artificial
intelligence (AI) especially the K-means algorithm (KMA) for the offloading decision and the genetic algorithm
(GA) for the scheduling and resources allocation. Finally, this method takes advantages of both the artificial
intelligence (k-means clustering) and genetic algorithm (GA) to optimize the makespan, the bandwidth and
the energy consumption. After comparing our work with authors works, we have found that our proposed is
we notice that the proposed algorithm is efficient in terms of makespan, bandwidth and energy consumptionCôte titre : MAI/0749 En ligne : https://drive.google.com/file/d/1RvsRQn9ecY65LzPjLco6gwyt0IDoU3uL/view?usp=drive [...] Format de la ressource électronique : Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité MAI/0749 MAI/0749 Mémoire Bibliothéque des sciences Anglais Disponible
Disponible