Edge-native Deep Learning

Edge-Native Deep Learning is a deep learning methodology specifically designed to natively operate within edge computing environments by optimizing model architecture, inference efficiency, and learning processes to meet the stringent constraints of latency, bandwidth, and hardware heterogeneity inherent to edge devices.

2

Publications

118

Citations

9

Authors

1

Institutions

Publications per year

2017–2026

2

Authors

9

  1. EP
    Ella Peltonen

    University of Oulu, Finland

    1 publications · 99 citations

    1

    h-index

  2. JR
    Jukka Riekki

    University of Oulu, Finland

    1 publications · 99 citations

    1

    h-index

  3. PP
    Pawani Porambage

    University of Oulu, Finland

    1 publications · 99 citations

    1

    h-index

  4. EH
    Erkki Harjula

    University of Oulu, Finland

    1 publications · 99 citations

    1

    h-index

  5. LL
    Lauri Lovén

    University of Oulu, Finland

    1 publications · 99 citations

    1

    h-index

1–5 of 9

Institutions

1

  1. Vellore Institute of Technology University

    Vellore, India

    1 h-index

    2 publications

    38 citations

  2. Beijing Institute of Technology

    Beijing, China

    1 publications

    19 citations

  3. Institute of Physics

    Beijing, China

    1 publications

    19 citations

1–3 of 1

Venues