Tools and methods for Edge-AI-systems

被引:0
|
作者
Schwabe, Nils [1 ]
Zhou, Yexu [2 ]
Hielscher, Leon [1 ]
Roeddiger, Tobias [2 ]
Riedel, Till [2 ]
Reiter, Sebastian [1 ]
机构
[1] FZI Res Ctr Informat Technol, Karlsruhe, Germany
[2] Karlsruher Inst Technol KIT, Inst Telemat, Karlsruhe, Germany
关键词
Edge-AI; machine learning; hardware acceleration; co-design; auto-ml;
D O I
10.1515/auto-2022-0023
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The enormous potential of artificial intelligence, especially artificial neural networks, when used for edge computing applications in cars, traffic lights or smart watches, has not yet been fully exploited today. The reasons for this are the computing, energy and memory requirements of modern neural networks, which typically cannot be met by embedded devices. This article provides a detailed summary of today's challenges and gives a deeper insight into existing solutions that enable neural network performance with modern HW/SW co-design techniques.
引用
收藏
页码:767 / 776
页数:10
相关论文
共 50 条
  • [31] Functionality Enhanced Memories for Edge-AI Embedded Systems
    Levisse, Alexandre
    Rios, Marco
    Simon, W-A
    Gaillardon, P-E
    Atienza, D.
    2019 19TH NON-VOLATILE MEMORY TECHNOLOGY SYMPOSIUM (NVMTS 2019), 2019,
  • [32] Edge AI: Systems Design and ML for IoT Data Analytics
    Marculescu, Radu
    Marculescu, Diana
    Ogras, Umit Y.
    KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 3565 - 3566
  • [33] 4th Workshop on Parallel AI and Systems for the Edge
    Akkus, Istemi Ekin
    Desai, Nirmit V
    Proceedings - 2022 IEEE 36th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2022, 2022, : 982 - 984
  • [34] Applying the ethics of AI: a systematic review of tools for developing and assessing AI-based systems
    Ortega-Bolanos, Ricardo
    Bernal-Salcedo, Joshua
    Ortiz, Mariana German
    Sarmiento, Julian Galeano
    Ruz, Gonzalo A.
    Tabares-Soto, Reinel
    ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (05)
  • [35] Seamless HW-accelerated AI serving in heterogeneous MEC Systems with AI@EDGE
    Tzenetopoulos, Achilleas
    Lentaris, George
    Leftheriotis, Aimilios
    Chrysomeris, Panos
    Palomares, Javier
    Coronado, Estefania
    Kazhamiakin, Raman
    Soudris, Dimitrios
    PROCEEDINGS OF THE 33RD INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE PARALLEL AND DISTRIBUTED COMPUTING, HPDC 2024, 2024,
  • [36] METHODS AND TOOLS FOR MODELLING REASONING IN DIAGNOSTIC SYSTEMS
    Eremeev, Alexander P.
    Vagin, Vadim N.
    ICEIS 2009 : PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS, VOL AIDSS, 2009, : 271 - 276
  • [37] Processes, Methods and Tools for Engineering Embedded Systems
    Ampatzoglou, Apostolos
    Hemila, Jukka
    PRODUCT-FOCUSED SOFTWARE PROCESS IMPROVEMENT, PROFES 2015, 2015, 9459 : XI - XIII
  • [38] Methods and tools for developing interactive information systems
    Wasserman, Anthony I.
    Conceptual Modelling in Information Systems Engineering, 2007, : 195 - 208
  • [39] Methods and Tools for Knowledge Exploitation in SOA Systems
    Adan Grzech
    Janusz Sobecki
    New Generation Computing, 2012, 30 : 95 - 97
  • [40] Methods and tools for profiling and control of distributed systems
    Sukharev, R.
    Lukyanchikov, O.
    Nikulchev, E.
    Biryukov, D.
    Ryadchikov, I.
    2017 WORKSHOP ON MATERIALS AND ENGINEERING IN AERONAUTICS (MEA2017), 2018, 312