EPISODE · Sep 7, 2022 · 19 MIN
Zero-Cost Proxies: How to find the best neural network without training (Ep. 201)
from Data Science at Home · host Francesco <frag> 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 Referenceshttps://www.technologyreview.com/2022/08/05/1056814/automation-ai-machine-learning-automl/https://iclr-blog-track.github.io/2022/03/25/zero-cost-proxies/ This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit datascienceathome.substack.com
NOW PLAYING
Zero-Cost Proxies: How to find the best neural network without training (Ep. 201)
No transcript for this episode yet
Similar Episodes
Apr 20, 2026 ·75m
Apr 16, 2026 ·84m
Apr 13, 2026 ·79m
Apr 6, 2026 ·116m
Mar 30, 2026 ·126m
Mar 27, 2026 ·17m