یادگیری عمیق در دستگاه های نهفته و تلفن همراه
ترجمه نشده

یادگیری عمیق در دستگاه های نهفته و تلفن همراه

عنوان فارسی مقاله: DMS: مقیاس بندی مدل پویا برای استنباط یادگیری عمیق آگاه از کیفیت در دستگاه های نهفته و تلفن همراه
عنوان انگلیسی مقاله: DMS: Dynamic Model Scaling for Quality-Aware Deep Learning Inference in Mobile and Embedded Devices
مجله/کنفرانس: دسترسی – IEEE Access
رشته های تحصیلی مرتبط: مهندسی کامپیوتر
گرایش های تحصیلی مرتبط: هوش مصنوعی، رایانش ابری
کلمات کلیدی فارسی: یادگیری عمیق، دستگاه های لبه ای، سیستم های نهفته، بهره وری انرژی، کنترل بازخورد، هرس فیلتر، دستگاه های تلفن همراه، فشرده سازی مدل، کیفیت خدمات، کیفیت خدمات (QoS)
کلمات کلیدی انگلیسی: Deep learning, edge devices, embedded systems, energy efficiency, feedback control, filter pruning, mobile devices, model compression, quality-of-service, QoS
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
نمایه: Scopus – Master Journals List – JCR
شناسه دیجیتال (DOI): https://doi.org/10.1109/ACCESS.2019.2954546
دانشگاه: Department of Embedded Systems Engineering, Incheon National University, Incheon 22012, South Korea
ناشر: آی تریپل ای - IEEE
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2019
ایمپکت فاکتور: 4.641 در سال 2018
شاخص H_index: 56 در سال 2019
شاخص SJR: 0.609 در سال 2018
شناسه ISSN: 2169-3536
شاخص Quartile (چارک): Q2 در سال 2018
فرمت مقاله انگلیسی: PDF
تعداد صفحات مقاله انگلیسی: 12
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: خیر
آیا این مقاله مدل مفهومی دارد: ندارد
آیا این مقاله پرسشنامه دارد: ندارد
آیا این مقاله متغیر دارد: ندارد
کد محصول: E14035
رفرنس: دارای رفرنس در داخل متن و انتهای مقاله
فهرست انگلیسی مطالب

Abstract


I. Introduction


II. Overview of DMS


III. Dynamic Model Scaling


IV. Evaluation


V. Related Works


Authors


Figures


References

نمونه متن انگلیسی مقاله

Abstract


Recently, deep learning has brought revolutions to many mobile and embedded systems that interact with the physical world using continuous video streams. Although there have been significant efforts to reduce the computational overheads of deep learning inference in such systems, previous approaches have focused on delivering ‘best-effort’ performance, resulting in unpredictable performance under variable environments. In this paper, we propose a runtime control method, called DMS (Dynamic Model Scaling), that enables dynamic resource-accuracy trade-offs to support various QoS requirements of deep learning applications. In DMS, the resource demands of deep learning inference can be controlled by adaptive pruning of computation-intensive convolution filters. DMS avoids irregularity of pruned models by reorganizing filters according to their importance so that varying number of filters can be applied efficiently. Since DMS’s pruning method incurs no runtime overhead and preserves the full capacity of original deep learning models, DMS can tailor the models at runtime for concurrent deep learning applications with their respective resource-accuracy trade-offs. We demonstrate the viability of DMS by implementing a prototype. The evaluation results demonstrate that, if properly coordinated with system level resource managers, DMS can support highly robust and efficient inference performance against unpredictable workloads.


Introduction


In the past few years, deep learning has emerged as a stateof-the-art approach that provides highly robust and accurate inference capability for many intelligent systems and services [1]. In particular, convolutional neural networks (CNNs or ConvNets) [2]–[4] have brought revolutions to computer vision applications [5]. Deep CNNs play as generic feature extractors for various visual recognition tasks such as image classification [3], object detection [6], semantic segmentation [7], and image retrieval [3]. Such visual recognition tasks are essential for many intelligent systems interacting with the physical world using continuous streaming of video inputs. Some examples are augmented reality wearables [8], camerabased surveillance, drones, autonomous vehicles [9], and live video analytics [5], to name a few. However, the size and complexity of deep learning models has been a major challenge for resource-constrained mobile and embedded devices, and there have been significant efforts to reduce the amount of computation of deep learning models either by compressing deep learning models at a modest loss of inference accuracy [10]–[۱۳] or by offloading inference workloads to custom accelerators [14]–[16]. Although these approaches have demonstrated significant gains in performance and efficiency, their resource demands are predetermined at development stages, incurring unpredictable ‘best-effort’ performance in highly dynamic environments. For instance, when a person with a wearable cognitive-assistance device walks to a more crowded area, more objects needs to be classified, resulting in sudden increases of overall inference latency and energy consumption [8].

  • اشتراک گذاری در

دیدگاه خود را بنویسید:

تاکنون دیدگاهی برای این نوشته ارسال نشده است

یادگیری عمیق در دستگاه های نهفته و تلفن همراه
نوشته های مرتبط
مقالات جدید
لوگوی رسانه های برخط

logo-samandehi

پیوندها