“We're able to train a classification algorithm ... when you have a string of negative results and then finally ... get to that positive result”

Latent Space: The AI Engineer Podcast · Synthesis Superintelligence: from Semiconductors to Superconductors - Periodic Labs’ Liam Fedus and Ekin Dogus Cubuk

Play from 56:37
56:37

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

Collect strings of negative experimental results, label them as failures, and train a classification algorithm to predict successful syntheses

Said nearby on the same subject

“We ask… tell me about your greatest successes and failures and then the extra step… tell me what caused your success and what caused your failure.”
AG
Adam Grant
Tony Robbins Podcast Daily ·
How they work Share this moment
“Off-label standard of care use of the device in a population that was really too small for a traditional trial... resulted in a successful PMA label expansion”
♫
Said on FDA Watch
How they work Share this moment
“Pre-registering experimental predictions by using for example Fatebook helps me notice when I should be surprised and update my model of the world.”
♫
Said on LessWrong (Curated & Popular)
“I put a little video up… 12 string or six string?… people were like, 12 string, six string.”
CA
Craig Stewart Adams
New Business Jump Start Show ·
How they work Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.