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?\nLet me introduce you to Zero-Cost proxies\n\xa0\n\xa0\nReferences\nhttps://www.technologyreview.com/2022/08/05/1056814/automation-ai-machine-learning-automl/\nhttps://iclr-blog-track.github.io/2022/03/25/zero-cost-proxies/