Neural network technologies are increasingly used in solving problems from various fields of industry, agriculture, medicine. The problems of optimizing the architecture and ANN hyperparameters focused on solving various classes of applied problems are caused by the need to improve the quality of deep ANN functioning. There are various methods for optimizing ANN hyperparameters, for example, using genetic algorithms, but they involve the creation of additional software. The «Keras Tuner» toolkit is known to optimize the procedures for the computer selection of the set of ANN hyperparameters. It is a toolkit for automated search for the optimal combination of network hyperparameters. In the «Keras Tuner» toolkit, you can choose mathematical methods such as random search, Bayesian optimization, Hyperband. In the numerical experiments carried out, 14 hyperparameters were varied: the number of blocks of convolutional layers and the filters forming them, the type of activation functions, the parameters of the “dropout” regulatory layers, and others. The investigated toolkit has demonstrated high efficiency of hyperparameter optimization while simultaneously varying several tens of parameters of the convolutional network. The calculation time for the studied ANN hyperparameters was several tens of hours, without the use of GPU graphics accelerators on the Colaboratory platform.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Computer Optimization of ANN Hyperparameters for Retrospective Information Processing


    Weitere Titelangaben:

    Lect. Notes in Networks, Syst.


    Beteiligte:
    Guda, Alexander (Herausgeber:in) / Melikhova, Elena (Autor:in) / Rogachev, Aleksey (Autor:in)

    Kongress:

    International School on Neural Networks, Initiated by IIASS and EMFCSC ; 2022 ; St.Petersburg, Russia February 08, 2022 - February 10, 2022



    Erscheinungsdatum :

    16.11.2022


    Format / Umfang :

    8 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    ICAS2016_0319: HYPERPARAMETERS OPTIMIZATION FOR ADAPTIVE DESIGN OF EXPERIMENTS APPLIED TO WIND TUNNEL TESTING

    Jin, H. / Lee, D. / Lee, J. et al. | British Library Conference Proceedings | 2016


    Analysis of Various Hyperparameters for Predicting Hypertension using Machine Learning Algorithms

    Duggal, Shallu / Sood, Shivani / Singh, Amanpreet et al. | IEEE | 2024


    Optimization of deep learning hyperparameters to predict amphibious aircraft aerodynamic coefficients using grid search cross validation

    Atmaja, Sigit Tri / Fajar, Muhammad / Fajar, Rizqon et al. | American Institute of Physics | 2023


    A Novel Method to Select Hyperparameters of the DBSCAN Algorithm for RADAR Applications

    Chauhan, Abhisha / Prajapati, Miit / Payghan, Vaibhav Santosh | SAE Technical Papers | 2024