Cost-effective Artificial Neural Networks

Zahra Atashgahi

doi:10.24963/ijcai.2023/810

Cost-effective Artificial Neural Networks

Zahra Atashgahi

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

83 Downloads (Pure)

Abstract

Deep neural networks (DNNs) have gained huge attention over the last several years due to their promising results in various tasks. However, due to their large model size and over-parameterization, they are recognized as being computationally demanding. Therefore, deep learning models are not well-suited to applications with limited computational resources and battery life. Current solutions to reduce computation costs mainly focus on inference efficiency while being resource-intensive during training. This Ph.D. research aims to address these challenges by developing cost-effective neural networks that can achieve decent performance on various complex tasks using minimum computational resources during training and inference of the network.

Original language	English
Title of host publication	Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23
Editors	Edith Elkind
Pages	7071-7072
Number of pages	2
ISBN (Electronic)	9781956792034
DOIs	https://doi.org/10.24963/ijcai.2023/810
Publication status	Published - Aug 2023
Event	32nd International Joint Conferences on Artificial Intelligence, IJCAI 2023 - Macao, China Duration: 19 Aug 2023 → 25 Aug 2023 Conference number: 32 https://ijcai-23.org/

Conference

Conference	32nd International Joint Conferences on Artificial Intelligence, IJCAI 2023
Abbreviated title	IJCAI 2023
Country/Territory	China
City	Macao
Period	19/08/23 → 25/08/23
Internet address	https://ijcai-23.org/

Access to Document

10.24963/ijcai.2023/810

0810Final published version, 60.7 KB

Cite this

@inproceedings{106ab2c8d2da425fa0e32fac333d03a3,

title = "Cost-effective Artificial Neural Networks",

abstract = "Deep neural networks (DNNs) have gained huge attention over the last several years due to their promising results in various tasks. However, due to their large model size and over-parameterization, they are recognized as being computationally demanding. Therefore, deep learning models are not well-suited to applications with limited computational resources and battery life. Current solutions to reduce computation costs mainly focus on inference efficiency while being resource-intensive during training. This Ph.D. research aims to address these challenges by developing cost-effective neural networks that can achieve decent performance on various complex tasks using minimum computational resources during training and inference of the network.",

author = "Zahra Atashgahi",

note = "Funding Information: I would like to express my sincere gratitude to my supervisors, Dr. Decebal Mocanu, Prof.dr. Raymond Veldhuis, and Prof.dr. Mykola Pechenizkiy for their guidance and mentorship. This research is partially funded by NWO EDIC project. Publisher Copyright: {\textcopyright} 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.; 32nd International Joint Conferences on Artificial Intelligence, IJCAI 2023, IJCAI 2023 ; Conference date: 19-08-2023 Through 25-08-2023",

year = "2023",

month = aug,

doi = "10.24963/ijcai.2023/810",

language = "English",

pages = "7071--7072",

editor = "Edith Elkind",

booktitle = "Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23",

url = "https://ijcai-23.org/",

}

TY - GEN

T1 - Cost-effective Artificial Neural Networks

AU - Atashgahi, Zahra

N1 - Conference code: 32

PY - 2023/8

Y1 - 2023/8

N2 - Deep neural networks (DNNs) have gained huge attention over the last several years due to their promising results in various tasks. However, due to their large model size and over-parameterization, they are recognized as being computationally demanding. Therefore, deep learning models are not well-suited to applications with limited computational resources and battery life. Current solutions to reduce computation costs mainly focus on inference efficiency while being resource-intensive during training. This Ph.D. research aims to address these challenges by developing cost-effective neural networks that can achieve decent performance on various complex tasks using minimum computational resources during training and inference of the network.

AB - Deep neural networks (DNNs) have gained huge attention over the last several years due to their promising results in various tasks. However, due to their large model size and over-parameterization, they are recognized as being computationally demanding. Therefore, deep learning models are not well-suited to applications with limited computational resources and battery life. Current solutions to reduce computation costs mainly focus on inference efficiency while being resource-intensive during training. This Ph.D. research aims to address these challenges by developing cost-effective neural networks that can achieve decent performance on various complex tasks using minimum computational resources during training and inference of the network.

U2 - 10.24963/ijcai.2023/810

DO - 10.24963/ijcai.2023/810

M3 - Conference contribution

SP - 7071

EP - 7072

BT - Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23

A2 - Elkind, Edith

T2 - 32nd International Joint Conferences on Artificial Intelligence, IJCAI 2023

Y2 - 19 August 2023 through 25 August 2023

ER -

Cost-effective Artificial Neural Networks

Abstract

Conference

Access to Document

Fingerprint

Cite this