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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rahman, Md Hafizur, Rizvee, Md Mashfiq, Shomaji, Sumaiya, Chakraborty, Prabuddha
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866916504375656448
author	Rahman, Md Hafizur Rizvee, Md Mashfiq Shomaji, Sumaiya Chakraborty, Prabuddha
author_facet	Rahman, Md Hafizur Rizvee, Md Mashfiq Shomaji, Sumaiya Chakraborty, Prabuddha
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2412_02116
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications Rahman, Md Hafizur Rizvee, Md Mashfiq Shomaji, Sumaiya Chakraborty, Prabuddha Machine Learning Computer Vision and Pattern Recognition 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.
title	ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications
topic	Machine Learning Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2412.02116