Slotting Learning Rate in Deep Neural Networks to Build Stronger Models

Dilip Kumar Sharma; Bhopendra Singh; Mamoona Anam; Klinge Orlando Villalba-Condori; Ankur Kumar Gupta; Ghassan Khazal Ali

doi:10.1109/ICOSEC51865.2021.9591733

Slotting Learning Rate in Deep Neural Networks to Build Stronger Models

Dilip Kumar Sharma, Bhopendra Singh, Mamoona Anam, Klinge Orlando Villalba-Condori, Ankur Kumar Gupta, Ghassan Khazal Ali

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In recent years, deep neural networks have made substantial progress in object recognition. However, one issue with deep learning is that it is currently unclear which proposed framework is exaggerated for a specific hitch. As a result, distinct dispositions are attempt before one that produces satisfactory results is discovered. This paper described a distributed supervised learning method for finding the best network architecture by modifying specifications for a perceived task dynamically. In the case of the MNIST information gathering, it is shown that asynchronous supervised learning can agree on a solution space. Setting several hyperparameters can be time-consuming when constructing neural networks. In this post, we'll provide you with some tips and instructions for better organizing your hyperparameter tuning process, which should help you find a good setting for the hyperparameters much faster.

Original language	English
Title of host publication	Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1587-1593
Number of pages	7
ISBN (Electronic)	9781665433686
DOIs	https://doi.org/10.1109/ICOSEC51865.2021.9591733
State	Published - 2021
Externally published	Yes
Event	2nd International Conference on Smart Electronics and Communication, ICOSEC 2021 - Trichy, India Duration: 7 Sep 2021 → 9 Sep 2021

Publication series

Name	Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

Conference

Conference	2nd International Conference on Smart Electronics and Communication, ICOSEC 2021
Country/Territory	India
City	Trichy
Period	7/09/21 → 9/09/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Artificial intelligence
Convolutional neural network
Deep learning
Hyper-parameter
Hyperparameter tuning
Machine learning
Neural networks
Orthogonal array

Access to Document

10.1109/ICOSEC51865.2021.9591733

Cite this

Sharma, D. K., Singh, B., Anam, M., Villalba-Condori, K. O., Gupta, A. K., & Ali, G. K. (2021). Slotting Learning Rate in Deep Neural Networks to Build Stronger Models. In Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021 (pp. 1587-1593). (Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOSEC51865.2021.9591733

Sharma, Dilip Kumar ; Singh, Bhopendra ; Anam, Mamoona et al. / Slotting Learning Rate in Deep Neural Networks to Build Stronger Models. Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 1587-1593 (Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021).

@inproceedings{4568fccf8ffa460dae23ad6e29b0a50b,

title = "Slotting Learning Rate in Deep Neural Networks to Build Stronger Models",

abstract = "In recent years, deep neural networks have made substantial progress in object recognition. However, one issue with deep learning is that it is currently unclear which proposed framework is exaggerated for a specific hitch. As a result, distinct dispositions are attempt before one that produces satisfactory results is discovered. This paper described a distributed supervised learning method for finding the best network architecture by modifying specifications for a perceived task dynamically. In the case of the MNIST information gathering, it is shown that asynchronous supervised learning can agree on a solution space. Setting several hyperparameters can be time-consuming when constructing neural networks. In this post, we'll provide you with some tips and instructions for better organizing your hyperparameter tuning process, which should help you find a good setting for the hyperparameters much faster. ",

keywords = "Artificial intelligence, Convolutional neural network, Deep learning, Hyper-parameter, Hyperparameter tuning, Machine learning, Neural networks, Orthogonal array",

author = "Sharma, {Dilip Kumar} and Bhopendra Singh and Mamoona Anam and Villalba-Condori, {Klinge Orlando} and Gupta, {Ankur Kumar} and Ali, {Ghassan Khazal}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; null ; Conference date: 07-09-2021 Through 09-09-2021",

year = "2021",

doi = "10.1109/ICOSEC51865.2021.9591733",

language = "Ingl{\'e}s",

series = "Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1587--1593",

booktitle = "Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021",

address = "Estados Unidos",

}

Sharma, DK, Singh, B, Anam, M, Villalba-Condori, KO, Gupta, AK & Ali, GK 2021, Slotting Learning Rate in Deep Neural Networks to Build Stronger Models. in Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021. Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021, Institute of Electrical and Electronics Engineers Inc., pp. 1587-1593, 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021, Trichy, India, 7/09/21. https://doi.org/10.1109/ICOSEC51865.2021.9591733

Slotting Learning Rate in Deep Neural Networks to Build Stronger Models. / Sharma, Dilip Kumar; Singh, Bhopendra; Anam, Mamoona et al.

Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 1587-1593 (Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Slotting Learning Rate in Deep Neural Networks to Build Stronger Models

AU - Sharma, Dilip Kumar

AU - Singh, Bhopendra

AU - Anam, Mamoona

AU - Villalba-Condori, Klinge Orlando

AU - Gupta, Ankur Kumar

AU - Ali, Ghassan Khazal

PY - 2021

Y1 - 2021

N2 - In recent years, deep neural networks have made substantial progress in object recognition. However, one issue with deep learning is that it is currently unclear which proposed framework is exaggerated for a specific hitch. As a result, distinct dispositions are attempt before one that produces satisfactory results is discovered. This paper described a distributed supervised learning method for finding the best network architecture by modifying specifications for a perceived task dynamically. In the case of the MNIST information gathering, it is shown that asynchronous supervised learning can agree on a solution space. Setting several hyperparameters can be time-consuming when constructing neural networks. In this post, we'll provide you with some tips and instructions for better organizing your hyperparameter tuning process, which should help you find a good setting for the hyperparameters much faster.

AB - In recent years, deep neural networks have made substantial progress in object recognition. However, one issue with deep learning is that it is currently unclear which proposed framework is exaggerated for a specific hitch. As a result, distinct dispositions are attempt before one that produces satisfactory results is discovered. This paper described a distributed supervised learning method for finding the best network architecture by modifying specifications for a perceived task dynamically. In the case of the MNIST information gathering, it is shown that asynchronous supervised learning can agree on a solution space. Setting several hyperparameters can be time-consuming when constructing neural networks. In this post, we'll provide you with some tips and instructions for better organizing your hyperparameter tuning process, which should help you find a good setting for the hyperparameters much faster.

KW - Artificial intelligence

KW - Convolutional neural network

KW - Deep learning

KW - Hyper-parameter

KW - Hyperparameter tuning

KW - Machine learning

KW - Neural networks

KW - Orthogonal array

UR - http://www.scopus.com/inward/record.url?scp=85123189981&partnerID=8YFLogxK

U2 - 10.1109/ICOSEC51865.2021.9591733

DO - 10.1109/ICOSEC51865.2021.9591733

M3 - Contribución a la conferencia

AN - SCOPUS:85123189981

T3 - Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

SP - 1587

EP - 1593

BT - Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 7 September 2021 through 9 September 2021

ER -

Sharma DK, Singh B, Anam M, Villalba-Condori KO, Gupta AK, Ali GK. Slotting Learning Rate in Deep Neural Networks to Build Stronger Models. In Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 1587-1593. (Proceedings - 2nd International Conference on Smart Electronics and Communication, ICOSEC 2021). doi: 10.1109/ICOSEC51865.2021.9591733

Slotting Learning Rate in Deep Neural Networks to Build Stronger Models

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this