LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 14

Search options

  1. Book ; Online: Modeling and Simulation for Electric Vehicle Applications

    Amine Fakhfakh, Mohamed

    2016  

    Keywords Automotive technology & trades ; electric vehicles, optimization, renewable energy, reliability, smart grid, electromagnetic radiation
    Language English
    Size 1 electronic resource (186 pages)
    Publisher IntechOpen
    Document type Book ; Online
    Note English
    HBZ-ID HT030646988
    ISBN 9789535166788 ; 9535166786
    Database ZB MED Catalogue: Medicine, Health, Nutrition, Environment, Agriculture

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: Bayesian optimization for sparse neural networks with trainable activation functions.

    Fakhfakh, Mohamed / Chaari, Lotfi

    IEEE transactions on pattern analysis and machine intelligence

    2024  Volume PP

    Abstract: In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that ... ...

    Abstract In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme has been tested across a diverse datasets, encompassing both classification and regression tasks, and implemented in various CNN architectures to demonstrate its versatility and effectiveness. Promising results demonstrate the usefulness of our proposed approach in improving models accuracy due to the proposed activation function and Bayesian estimation of the parameters.
    Language English
    Publishing date 2024-04-10
    Publishing country United States
    Document type Journal Article
    ISSN 1939-3539
    ISSN (online) 1939-3539
    DOI 10.1109/TPAMI.2024.3387073
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Bayesian optimization for sparse neural networks with trainable activation functions

    Fakhfakh, Mohamed / Chaari, Lotfi

    2023  

    Abstract: In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that ... ...

    Abstract In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme is tested on three datasets with three different CNNs. Promising results demonstrate the usefulness of our proposed approach in improving model accuracy due to the proposed activation function and Bayesian estimation of the parameters.
    Keywords Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Statistics - Methodology
    Subject code 006
    Publishing date 2023-04-10
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article: Non-smooth Bayesian learning for artificial neural networks.

    Fakhfakh, Mohamed / Chaari, Lotfi / Bouaziz, Bassem / Gargouri, Faiez

    Journal of ambient intelligence and humanized computing

    2022  , Page(s) 1–19

    Abstract: Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work ... ...

    Abstract Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively such as gradient-based method, Newton-type method, meta-heuristic method. For the sake of efficiency, regularization is generally used. When non-smooth regularizers are used especially to promote sparse networks, such as the
    Language English
    Publishing date 2022-06-25
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 2543187-0
    ISSN 1868-5145 ; 1868-5137
    ISSN (online) 1868-5145
    ISSN 1868-5137
    DOI 10.1007/s12652-022-04073-8
    Database MEDical Literature Analysis and Retrieval System OnLINE

    Full text online

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  5. Book: Atlas de Tunisie

    Fakhfakh, Mohamed

    (Les atlas Jeune Afrique)

    1979  

    Author's details Mohamed Fakhfakh [Hrsg.]
    Series title Les atlas Jeune Afrique
    Language French
    Size 72 S
    Publishing place Paris
    Document type Book
    ISBN 2852581523 ; 9782852581524
    Database Former special subject collection: coastal and deep sea fishing

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article: Sensitivity of Zymoseptoria tritici Isolates from Tunisia to Pyraclostrobin, Fluxapyroxad, Epoxiconazole, Metconazole, Prochloraz and Tebuconazole

    Taher, Karima / Graf, Sarah / Fakhfakh, Mohamed Moez / Salah, Halim B. H / Yahyaoui, Amor / Rezgui, Salah / Nasraoui, Bouzid / Stammler, Gerd

    Phytopathologische Zeitschrift. 2014 Aug., v. 162, no. 7-8

    2014  

    Abstract: Sensitivity of 159 isolates of Zymoseptoria tritici collected from durum wheat fields in Tunisia in 2012 was analysed towards pyraclostrobin, fluxapyroxad, epoxiconazole, metconazole, prochloraz and tebuconazole using microtiter tests. All isolates were ... ...

    Abstract Sensitivity of 159 isolates of Zymoseptoria tritici collected from durum wheat fields in Tunisia in 2012 was analysed towards pyraclostrobin, fluxapyroxad, epoxiconazole, metconazole, prochloraz and tebuconazole using microtiter tests. All isolates were found to be highly sensitive to pyraclostrobin with EC₅₀ <0.01� mg/l with the exception of three isolates from the same field with higher EC₅₀ values (>0.5� mg/l). These three isolates carried a mutation in the cytochrome b gene encoding the G143A substitution. This is the first report of quinone outside inhibitors (QoI) resistance in Z.� tritici in Tunisia. Sensitivity towards r fluxapyroxad was in a narrow range with EC₅₀ values ranging between 0.013 and 0.125� mg/l, which can serve as baseline sensitivity data for the future. Demethylation inhibitors sensitivity varied across a broad range with the data indicating a slight shift in sensitivity when compared to a previous study on the 2010 population. No highly sensitive strains were isolated from samples from fields, which had received three or four DMI applications.
    Keywords cytochrome b ; durum wheat ; genes ; mutation ; prochloraz ; pyraclostrobin ; tebuconazole ; Tunisia
    Language English
    Dates of publication 2014-08
    Size p. 442-448.
    Publishing place Blackwell Science
    Document type Article
    ZDB-ID 2020539-9
    ISSN 1439-0434 ; 0931-1785
    ISSN (online) 1439-0434
    ISSN 0931-1785
    DOI 10.1111/jph.12210
    Database NAL-Catalogue (AGRICOLA)

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  7. Article: Le cas de la Tunisie

    Fakhfakh, Mohamed

    Syst`eme urbain et développement au Maghreb , p. 117-128

    1980  , Page(s) 117–128

    Author's details Mohamed Fakhfakh
    Keywords Stadtraum ; Tunesien
    Size graph. Darst
    Publisher Céres Prod.
    Publishing place Tunis
    Document type Article
    Database ECONomics Information System

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Book: La grande exploitation agricole dans la région sfaxienne

    Fakhfakh, Mohamed

    (Cahiers du C.E.R.E.S. : Série géographique ; 3)

    1976  

    Author's details Mohamed Fakhfakh
    Series title Cahiers du C.E.R.E.S. : Série géographique ; 3
    Keywords Agrarwirtschaft der Landesteile ; Steppe ; Agrarbodenschutz ; Agrarwirtschaftliches Wachstum ; Agrarverfassung ; Tunesien ; Sfax
    Language French
    Size 294 S, Ill., graph. Darst., Kt, 24 cm
    Publisher Univ. de Tunis, Centre d'Études et de Recherches Économiques et Sociales
    Publishing place Tunis
    Document type Book
    Database ECONomics Information System

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  9. Article: Croissance urbaine de lʹagglomération sfaxienne

    Fakhfakh, Mohamed

    Revue tunisienne des sciences sociales : publ. du Centre d'Etudes et de Recherches Economiques et Sociales, Université de Tunis Vol. 8 , p. 173-191

    1971  Volume 8, Page(s) 173–191

    Author's details Mohamed Fakhfakh
    Keywords Stadtraum ; Tunesien ; Sfax
    Publisher CERES
    Publishing place Tunis
    Document type Article
    ZDB-ID 300828-9
    Database ECONomics Information System

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Article: Industrialisation et dynamique urbaine

    Fakhfakh, Mohamed

    Revue tunisienne des sciences sociales : publ. du Centre d'Etudes et de Recherches Economiques et Sociales, Université de Tunis Vol. 8 , p. 69-92

    1971  Volume 8, Page(s) 69–92

    Author's details Mohamed Fakhfakh
    Keywords Standort ; Stadtraum ; Tunesien ; Sfax
    Publisher CERES
    Publishing place Tunis
    Document type Article
    ZDB-ID 300828-9
    Database ECONomics Information System

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top