ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications

Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rahman, Md Hafizur, Rizvee, Md Mashfiq, Shomaji, Sumaiya, Chakraborty, Prabuddha
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Rahman, Md Hafizur
Rizvee, Md Mashfiq
Shomaji, Sumaiya
Chakraborty, Prabuddha
description Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.
doi_str_mv 10.48550/arxiv.2412.02116
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2412_02116</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2412_02116</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2412_021163</originalsourceid><addsrcrecordid>eNqFjsEKgkAURWfTIqoPaNX7Ac0xjWgnkRhUBLqXxzTSwzHlOVr9fSXtWx0uHLhHiLn03GATht4S-Um96wfSdz1fyvVYZIdjlCZbiODC-krKUq_hrDtGAxGrG1mtbMcaUo2fCTFjpR81l1DUDKfOWHIybEuImsaQQkv1vZ2KUYGm1bMfJ2IR77Nd4gz_ecNUIb_yb0c-dKz-G29wRj0j</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications</title><source>arXiv.org</source><creator>Rahman, Md Hafizur ; Rizvee, Md Mashfiq ; Shomaji, Sumaiya ; Chakraborty, Prabuddha</creator><creatorcontrib>Rahman, Md Hafizur ; Rizvee, Md Mashfiq ; Shomaji, Sumaiya ; Chakraborty, Prabuddha</creatorcontrib><description>Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.</description><identifier>DOI: 10.48550/arxiv.2412.02116</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2024-12</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2412.02116$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2412.02116$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Rahman, Md Hafizur</creatorcontrib><creatorcontrib>Rizvee, Md Mashfiq</creatorcontrib><creatorcontrib>Shomaji, Sumaiya</creatorcontrib><creatorcontrib>Chakraborty, Prabuddha</creatorcontrib><title>ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications</title><description>Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjsEKgkAURWfTIqoPaNX7Ac0xjWgnkRhUBLqXxzTSwzHlOVr9fSXtWx0uHLhHiLn03GATht4S-Um96wfSdz1fyvVYZIdjlCZbiODC-krKUq_hrDtGAxGrG1mtbMcaUo2fCTFjpR81l1DUDKfOWHIybEuImsaQQkv1vZ2KUYGm1bMfJ2IR77Nd4gz_ecNUIb_yb0c-dKz-G29wRj0j</recordid><startdate>20241202</startdate><enddate>20241202</enddate><creator>Rahman, Md Hafizur</creator><creator>Rizvee, Md Mashfiq</creator><creator>Shomaji, Sumaiya</creator><creator>Chakraborty, Prabuddha</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241202</creationdate><title>ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications</title><author>Rahman, Md Hafizur ; Rizvee, Md Mashfiq ; Shomaji, Sumaiya ; Chakraborty, Prabuddha</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2412_021163</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Rahman, Md Hafizur</creatorcontrib><creatorcontrib>Rizvee, Md Mashfiq</creatorcontrib><creatorcontrib>Shomaji, Sumaiya</creatorcontrib><creatorcontrib>Chakraborty, Prabuddha</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Rahman, Md Hafizur</au><au>Rizvee, Md Mashfiq</au><au>Shomaji, Sumaiya</au><au>Chakraborty, Prabuddha</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications</atitle><date>2024-12-02</date><risdate>2024</risdate><abstract>Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time.</abstract><doi>10.48550/arxiv.2412.02116</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2412.02116
ispartof
issn
language eng
recordid cdi_arxiv_primary_2412_02116
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T05%3A57%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ILASH:%20A%20Predictive%20Neural%20Architecture%20Search%20Framework%20for%20Multi-Task%20Applications&rft.au=Rahman,%20Md%20Hafizur&rft.date=2024-12-02&rft_id=info:doi/10.48550/arxiv.2412.02116&rft_dat=%3Carxiv_GOX%3E2412_02116%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true