“We then collected those corrections and then basically fed them back into the training data, retrained the models. They then got better.”
♫
Said on The Leadership in Insurance Podcast - Insurtech & Innovation
“When you retrain it with modern settings, about 70% readable; build a modern design ... readability jumps to 99%.”
The AI Daily Brief: Artificial Intelligence News and Analysis · A Potentially Historic AI Breakthrough
Play from 13:39
13:39
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
retrained a modern-design image model of the same size and data as the 2014 Inception v1 model
99% of last-layer detectors readable
Said nearby on the same subject
“You need more pre-training data… give the model a bunch of data and think… transform this data… pre-trained on it would make the model smarter”
♫
Said on "The Cognitive Revolution"
“The model can also generate videos… the model can also generate its own training data so that becomes a self-fulfilling flywheel”
♫
Said on Latent Space: The AI Engineer Podcast
“The model can pretty much be the same. It's more a matter of intent... you add the objective on top of a simulation model.”
TV
Tim Varelmann
Software Engineering Radio - the podcast for professional software developers ·
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 monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.