Zero-Cost Proxies: How to find the best neural network without training (Ep. 201)

Data Science at Home

Sep 7 2022 • 19 mins

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/

You Might Like

Paradigm Shift
Paradigm Shift
Microsoft India
Darknet Diaries
Darknet Diaries
Jack Rhysider
Waveform: The MKBHD Podcast
Waveform: The MKBHD Podcast
Vox Media Podcast Network
WSJ’s The Future of Everything
WSJ’s The Future of Everything
The Wall Street Journal
Talk Python To Me
Talk Python To Me
Michael Kennedy (@mkennedy)
System Design
System Design
Wes and Kevin
The Stack Overflow Podcast
The Stack Overflow Podcast
The Stack Overflow Podcast
Super Data Science Podcast with Jon Krohn
Super Data Science Podcast with Jon Krohn
Jon Krohn and Guests on Machine Learning, A.I., and Data-Career Success
CyberWire Daily
CyberWire Daily
N2K Networks
Product Management: The Journey  0 - 1 - 100
Product Management: The Journey 0 - 1 - 100
Krishna Ramalingam & Mayank Gelani
a16z Podcast
a16z Podcast
Andreessen Horowitz
TED Tech
TED Tech
TED Tech