NLP Wiki

User Tools

Site Tools

Trace: • edge_computing
ml:edge_computing

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
ml:edge_computing [2022/08/01 06:47] – jmflanigml:edge_computing [2025/03/26 20:13] (current) – [Related Pages] jmflanig
Line 1: Line 1:
 ====== Edge Computing for Neural Networks ====== ====== Edge Computing for Neural Networks ======
 +Sometimes called tiny machine learning (TinyML) which is machine learning for resourced constrained devices.
 ===== Overviews ===== ===== Overviews =====
   * [[https://arxiv.org/pdf/1910.10231.pdf|Voghoei et al 2019 - Deep Learning at the Edge]]   * [[https://arxiv.org/pdf/1910.10231.pdf|Voghoei et al 2019 - Deep Learning at the Edge]]
Line 6: Line 6:
   * [[https://arxiv.org/pdf/1907.08349.pdf|Wang et al 2019 - Convergence of Edge Computing and Deep Learning: A Comprehensive Survey]]   * [[https://arxiv.org/pdf/1907.08349.pdf|Wang et al 2019 - Convergence of Edge Computing and Deep Learning: A Comprehensive Survey]]
   * [[https://arxiv.org/pdf/2003.12172.pdf|Xu et al 2020 - Edge Intelligence: Architectures, Challenges, and Applications]]   * [[https://arxiv.org/pdf/2003.12172.pdf|Xu et al 2020 - Edge Intelligence: Architectures, Challenges, and Applications]]
 +  * [[https://arxiv.org/pdf/2311.11883|2023 - Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review]]
  
 ===== Papers ===== ===== Papers =====
Line 12: Line 13:
   * [[https://arxiv.org/pdf/2004.05801.pdf|Sankar et al 2020 - ProFormer: Towards On-Device LSH Projection Based Transformers]]   * [[https://arxiv.org/pdf/2004.05801.pdf|Sankar et al 2020 - ProFormer: Towards On-Device LSH Projection Based Transformers]]
   * [[https://www.aclweb.org/anthology/2021.eacl-main.238.pdf|Zhao et al 2021 - Extremely Small BERT Models from Mixed-Vocabulary Training]] Compresses BERT for edge devices by compressing the input word embeddings   * [[https://www.aclweb.org/anthology/2021.eacl-main.238.pdf|Zhao et al 2021 - Extremely Small BERT Models from Mixed-Vocabulary Training]] Compresses BERT for edge devices by compressing the input word embeddings
 +
 +===== Software =====
 +  * [[https://pytorch.org/mobile/home/|PyTorch Mobile]]
 +  * [[https://www.tensorflow.org/lite|TensorFlow Lite]]
 +  * [[https://www.tensorflow.org/lite/microcontrollers|TensorFlow Lite for Microcontrollers]]
  
 ===== Conferences and Workshops ===== ===== Conferences and Workshops =====
-  * [[https://mlsys.org/|MLSys]]+  * [[https://mlsys.org/|MLSys]] - Has some mobile, on-device, or edge computing papers 
 +  * [[https://www.tinyml.org/|TinyML]] (Educational - I don't think they publish papers)
  
 ===== Related Pages ===== ===== Related Pages =====
 +  * [[Efficient NNs]]
   * [[Model Compression]]   * [[Model Compression]]
  
  
ml/edge_computing.1659336425.txt.gz · Last modified: 2023/06/15 07:36 (external edit)
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki