Algorithms for speeding-up the deep neural networks for detecting plant disease

Lida Kouhalvandi, Ece Olcay Gunes, Serdar Ozoguz

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

3 Atıf (Scopus)

Özet

In designing an artificial network, different parameters such as activation functions, hyper-parameters, etc. are considered. Dealing with large number of parameters and also the functions that are expensive for evalualtion are very hard tasks. In this case, it is logical to find methods that results in smaller number of evaluations and improvements in performance. There are various techniques for multiobjective Bayesian optimization in deep learning structure. S-metric selection efficient global optimization (SMS-EGO) and DIRECT are one of the many techniques for multiobjective Bayesian optimization. In this paper, SMS-EGO and DIRECT techniques are applied to deep learning model and the average number of evaluations of each objective including time and error are investigated. For training and validating the deep network, a number of images present various diseases in leaves are provided from Plant Village data set. The simulation results show that by using SMSEGO technique, performance is improved and average time per iteration is faster.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığı2019 8th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2019
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)9781728121161
DOI'lar
Yayın durumuYayınlandı - Tem 2019
Etkinlik8th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2019 - Istanbul, Turkey
Süre: 16 Tem 201919 Tem 2019

Yayın serisi

Adı2019 8th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2019

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???8th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2019
Ülke/BölgeTurkey
ŞehirIstanbul
Periyot16/07/1919/07/19

Bibliyografik not

Publisher Copyright:
© 2019 IEEE.

Finansman

This work is funded by T.R. Ministry of Food,Agriculture and Livestock, ITU TARB1L Environmental Agriculture Informatics Applied Research Center.978-1-7281-2116-1/19/$31.00 ©2019 IEEE

FinansörlerFinansör numarası
ITU TARB1L Environmental Agriculture Informatics Applied Research
Ministry of Food,Agriculture and Livestock
TARB1L Environmental Agriculture Informatics Applied Research Center.978-1-7281-2116-1Center.978-1-7281-2116-1/19
IEEE Foundation

    Parmak izi

    Algorithms for speeding-up the deep neural networks for detecting plant disease' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

    Alıntı Yap