Hand tuning convolutional neural networks (CNN) for performance optimization can be tedious. A novel approach using a genetic algorithm to automate CNN hyper-parameter adjustment is proposed. This automated approach shows a 5% accuracy improvement over hand tuned methods and highly energy efficient networks on the Intel Movidius Compute Stick.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CNN Optimization with a Genetic Algorithm


    Contributors:


    Publication date :

    2019-07-01


    Size :

    878765 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Flight Route Optimization With Genetic Algorithm

    Lu, Y. / Bo, R. | British Library Conference Proceedings | 2002


    Composite Structure Optimization with Genetic Algorithm

    Deslandes, O. / European Space Agency | British Library Conference Proceedings | 2014


    Ascent Trajectory Optimization Using Genetic Algorithm

    Zeeshan, Qasim / Waheed, Abdul / Linshu, He | AIAA | 2009