Sept. 7, 2022, 5:14 a.m. | Francesco Gadaleta

Data Science at Home datascienceathome.podbean.com

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


  1. https://www.technologyreview.com/2022/08/05/1056814/automation-ai-machine-learning-automl/

  2. https://iclr-blog-track.github.io/2022/03/25/zero-cost-proxies/

cost network neural network proxies training

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

Artificial Intelligence – Bioinformatic Expert

@ University of Texas Medical Branch | Galveston, TX

Lead Developer (AI)

@ Cere Network | San Francisco, US