09.07.2022 - By Francesco Gadaleta
Neural networks are becoming massive monsters that are hard to train (without the "regular" 12 last-generation GPUs).Is there a way to skip that?
Let me introduce you to Zero-Cost proxies
References
https://www.technologyreview.com/2022/08/05/1056814/automation-ai-machine-learning-automl/
https://iclr-blog-track.github.io/2022/03/25/zero-cost-proxies/