Adaptive and Energy-Efficient Architectures for Machine Learning: Challenges, Opportunities, and Research Roadmap

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F17%3APU126431" target="_blank" >RIV/00216305:26230/17:PU126431 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11474" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11474</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISVLSI.2017.124" target="_blank" >10.1109/ISVLSI.2017.124</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Adaptive and Energy-Efficient Architectures for Machine Learning: Challenges, Opportunities, and Research Roadmap

Popis výsledku v původním jazyce

Gigantic rates of data production in the era of Big Data, Internet of Thing (IoT) / Internet of Everything (IoE), and Cyber Physical Systems (CSP) pose incessantly escalating demands for massive data processing, storage, and transmission while continuously interacting with the physical world under unpredictable, harsh, and energy-/power constrained scenarios. Therefore, such systems need to support not only the high performance capabilities at tight power/energy envelop, but also need to be intelligent/cognitive, self-learning, and robust. As a result, a hype in the artificial intelligence research (e.g., deep learning and other machine learning techniques) has surfaced in numerous communities. This paper discusses the challenges and opportunities for building energy-efficient and adaptive architectures for machine learning. In particular, we focus on brain-inspired emerging computing paradigms, such as approximate computing; that can further reduce the energy requirements of the system. First, we guide through an approximate computing based methodology for development of energy-efficient accelerators, specifically for convolutional Deep Neural Networks (DNNs). We show that in-depth analysis of datapaths of a DNN allows better selection of Approximate Computing modules for energy-efficient accelerators. Further, we show that a multi-objective evolutionary algorithm can be used to develop an adaptive machine learning system in hardware. At the end, we summarize the challenges and the associated research roadmap that can aid in developing energy-efficient and adaptable hardware accelerators for machine learning.

Název v anglickém jazyce

Adaptive and Energy-Efficient Architectures for Machine Learning: Challenges, Opportunities, and Research Roadmap

Popis výsledku anglicky

Gigantic rates of data production in the era of Big Data, Internet of Thing (IoT) / Internet of Everything (IoE), and Cyber Physical Systems (CSP) pose incessantly escalating demands for massive data processing, storage, and transmission while continuously interacting with the physical world under unpredictable, harsh, and energy-/power constrained scenarios. Therefore, such systems need to support not only the high performance capabilities at tight power/energy envelop, but also need to be intelligent/cognitive, self-learning, and robust. As a result, a hype in the artificial intelligence research (e.g., deep learning and other machine learning techniques) has surfaced in numerous communities. This paper discusses the challenges and opportunities for building energy-efficient and adaptive architectures for machine learning. In particular, we focus on brain-inspired emerging computing paradigms, such as approximate computing; that can further reduce the energy requirements of the system. First, we guide through an approximate computing based methodology for development of energy-efficient accelerators, specifically for convolutional Deep Neural Networks (DNNs). We show that in-depth analysis of datapaths of a DNN allows better selection of Approximate Computing modules for energy-efficient accelerators. Further, we show that a multi-objective evolutionary algorithm can be used to develop an adaptive machine learning system in hardware. At the end, we summarize the challenges and the associated research roadmap that can aid in developing energy-efficient and adaptable hardware accelerators for machine learning.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20206 - Computer hardware and architecture

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2017 IEEE Computer Society Annual Symposium on VLSI

ISBN

978-1-5090-6762-6

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

627-632

Název nakladatele

IEEE Computer Society Press

Místo vydání

Los Alamitos

Místo konání akce

Bochum

Datum konání akce

3. 7. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—