mdh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
ADONN: Adaptive Design of Optimized Deep Neural Networks for Embedded Systems
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0001-7586-0409
2018 (English)In: 21st Euromicro Conference on Digital System Design DSD'18, 2018, p. 397-404, article id 8491845Conference paper, Published paper (Refereed)
Abstract [en]

Nowadays, many modern applications, e.g. autonomous system, and cloud data services need to capture and process a big amount of raw data at runtime, that ultimately necessitates a high-performance computing model. Deep Neural Network (DNN) has already revealed its learning capabilities in runtime data processing for modern applications. However, DNNs are becoming more deep sophisticated models for gaining higher accuracy which require a remarkable computing capacity. Considering high-performance cloud infrastructure as a supplier of required computational throughput is often not feasible. Instead, we intend to find a near-sensor processing solution which will lower the need for network bandwidth and increase privacy and power efficiency, as well as guaranteeing worst-case response-times. Toward this goal, we introduce ADONN framework, which aims to automatically design a highly robust DNN architecture for embedded devices as the closest processing unit to the sensors. ADONN adroitly searches the design space to find improved neural architectures. Our proposed framework takes advantage of a multi-objective evolutionary approach, which exploits a pruned design space inspired by a dense architecture. Unlike recent works that mainly have tried to generate highly accurate networks, ADONN also considers the network size factor as the second objective to build a highly optimized network fitting with limited computational resource budgets while delivers comparable accuracy level. In comparison with the best result on CIFAR-10 dataset, a generated network by ADONN presents up to 26.4 compression rate while loses only 4% accuracy. In addition, ADONN maps the generated DNN on the commodity programmable devices including ARM Processor, Hiph-Performance CPU, GPU, and FPGA.

Place, publisher, year, edition, pages
2018. p. 397-404, article id 8491845
Keywords [en]
Neural Architectural Search, Approximation Computing, Neural Processing Unit, Multi-Objective Optimization
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:mdh:diva-40876DOI: 10.1109/DSD.2018.00074Scopus ID: 2-s2.0-85056450132ISBN: 9781538673768 (electronic)OAI: oai:DiVA.org:mdh-40876DiVA, id: diva2:1249773
Conference
21st Euromicro Conference on Digital System Design DSD'18, 29 Aug 2018, Prague, Czech Republic
Projects
DPAC - Dependable Platforms for Autonomous systems and ControlFAST-ARTS: Fast and Sustainable Analysis Techniques for Advanced Real-Time SystemsDeepMaker: Deep Learning Accelerator on Commercial Programmable DevicesAvailable from: 2018-09-20 Created: 2018-09-20 Last updated: 2018-11-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Loni, MohammadDaneshtalab, Masoud

Search in DiVA

By author/editor
Loni, MohammadDaneshtalab, MasoudSjödin, Mikael
By organisation
Embedded Systems
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 98 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf