Jump to content

Neural Network Intelligence

From Wikipedia, the free encyclopedia
NNI (Neural Network Intelligence)
Original author(s)Microsoft Research
Developer(s)Microsoft
Initial release2018; 6 years ago (2018)[1]
Stable release
v2.10[2] / November 14, 2022; 23 months ago (2022-11-14)
Repositorygithub.com/microsoft/nni
Written inPython
Operating systemWindows, macOS, Ubuntu
PlatformCross-platform
TypeAutoML toolkit
LicenseMIT License
Websitenni.readthedocs.io

NNI (Neural Network Intelligence) is a free and open-source AutoML toolkit developed by Microsoft.[3][4] It is used to automate feature engineering, model compression, neural architecture search, and hyper-parameter tuning.[5][6]

The source code is licensed under MIT License and available on GitHub.[7]

See also

[edit]

References

[edit]
  1. ^ "Tags · microsoft/nni · GitHub". GitHub. 10 September 2021.
  2. ^ "Tags · microsoft/nni · GitHub". GitHub. 28 June 2022.
  3. ^ Raschka, Sebastian; Patterson, Joshua; Nolet, Corey (April 11, 2020). "Machine Learning in Python: Main Developments and Technology Trends in Data Science, Machine Learning, and Artificial Intelligence". Information. 11 (4): 193. arXiv:2002.04803. doi:10.3390/info11040193.
  4. ^ "Open Source AutoML Tools: AutoGluon, TransmogrifAI, Auto-sklearn, and NNI". Bizety. June 16, 2020.
  5. ^ Heller, Martin (August 21, 2019). "Automated machine learning or AutoML explained". InfoWorld.
  6. ^ "15 Undiscovered & Open Source Machine Learning Frameworks You Need to Know in 2020". freeCodeCamp.org. June 4, 2020.
  7. ^ "microsoft/nni". August 11, 2020 – via GitHub.

Further reading

[edit]
  • Gridin, Ivan (2022). Automated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python. Apress. ISBN 978-1484281482.
[edit]