Why care about Neural Architecture Search (NAS)?

Описание: In this video, we'll learn an overview of Neural Architecture Search (NAS) and why you should care about it! We'll discuss the motivation behind NAS, NAS approaches (reinforcement learning, neuroevolution, DARTS, one-shot NAS, and training-free methods), and NAS benchmarks as well.

TIMESTAMPS:
0:00 Intro
0:15 Motivation
0:41 Traditional vs. NAS
1:01 Search methods
2:52 Reproducibility problem
3:41 NAS benchmarks
4:05 Other applications
4:18 Why care?
5:10 Summary

Image Credits:
https://commons.wikimedia.org/wiki/Fi...
https://www.flickr.com/photos/clinica...
https://images.squarespace-cdn.com/co...
  / 1*0dswfuc0pdmcamhjuh7wqg.png  
https://commons.wikimedia.org/wiki/Fi...
https://commons.wikimedia.org/wiki/Fi...
https://commons.wikimedia.org/wiki/Fi...

References:
Ahn, J. S., Shin, S., Yang, S. A., Park, E. K., Kim, K. H., Cho, S. I., ... & Kim, S. (2023). Artificial Intelligence in Breast Cancer Diagnosis and Personalized Medicine. Journal of Breast Cancer, 26(5), 405.
Christensen, J. (2023, August 1). AI-supported mammogram screening increases breast cancer detection by 20%, study finds. CNN. https://www.cnn.com/2023/08/01/health...
Gridin, I. (2022). One-Shot Neural Architecture Search. In Automated Deep Learning Using Neural Network Intelligence: Develop and Design PyTorch and TensorFlow Models Using Python (pp. 257-318). Berkeley, CA: Apress.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Klyuchnikov, N., Trofimov, I., Artemova, E., Salnikov, M., Fedorov, M., Filippov, A., & Burnaev, E. (2022). Nas-bench-nlp: neural architecture search benchmark for natural language processing. IEEE Access, 10, 45736-45747.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
Liu, H., Simonyan, K., & Yang, Y. (2018). Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055.
Mehrotra, A., Ramos, A. G. C., Bhattacharya, S., Dudziak, Ł., Vipperla, R., Chau, T., ... & Lane, N. D. (2020, October). NAS-Bench-ASR: Reproducible neural architecture search for speech recognition. In International Conference on Learning Representations.
Mellor, J., Turner, J., Storkey, A., & Crowley, E. J. (2021, July). Neural architecture search without training. In International conference on machine learning (pp. 7588-7598). PMLR.
Ouyang, A. (2023, January 20). MIT researchers develop an AI model that can detect future lung cancer risk. MIT News | Massachusetts Institute of Technology. https://news.mit.edu/2023/ai-model-ca...
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Stanley, K. O., Clune, J., Lehman, J., & Miikkulainen, R. (2019). Designing neural networks through neuroevolution. Nature Machine Intelligence, 1(1), 24-35.
Zoph, B., & Le, Q. V. (2016). Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578.