DOI QR코드

DOI QR Code

Comparison of On-Device AI Software Tools

  • Received : 2022.05.28
  • Accepted : 2022.06.09
  • Published : 2022.06.30

Abstract

As the number of data and devices explodes, centralized data processing and AI analysis have limitations due to the load on the network and cloud. On-device AI technology can provide intelligent services without overloading the network and cloud because the device itself performs AI models. Accordingly, the need for on-device AI technology is emerging. Many smartphones are equipped with On-Device AI technology to support the use of related functions. In this paper, we compare software tools that implement On-Device AI.

Keywords

References

  1. Y. Lee, "Analysis of Automatic Machine Learning Solution Trends of Startups," Vol.8, No.2, International Journal of Advanced Culture Technology, 2020, https://doi.org/10.17703/IJACT.2020.8.2.297.
  2. Y. Lee, "Analysis on trends of machine learning-as-a-service," Vol. 6, No. 4, International Journal of Advanced Culture Technology, 2018, https://doi.org /10.17703//IJACT2018.6.4.303.
  3. On-Device Artificial Intelligence: A Game Changer, https://innodata.com/on-device-artificial-intelligence/
  4. S. Lee, "Trend of On-Device AI Hardware and Software Technology Development," Weekly Technology Trend, No. 2028, 2021.
  5. ML Kit, https://developers.google.com/ml-kit.
  6. CoreML, https://developer.apple.com/machine-learning/core-ml/.
  7. TensorRT, https://developer.nvidia.com/tensorrt.
  8. Arm Compute Library, https://www.arm.com/technologies/compute-library.
  9. AI Model Efficiency Toolkit(AIMET), https://developer.qualcomm.com/software/ai-model-efficiency-toolkit.