Episode 83 - Multimodale Modelle - Q-Former

from Knowledge Science - Alles über KI, ML und NLP · host Sigurd Schacht, Carsten Lanquillon

Send us Fan MailIn der heutigen Sendung steigen wir noch einmal in die Welt der multimodalen Modelle ein. Diesmal sprechen wir über das Bindeglied zwischen dem uni-modalen Bildverarbeitungsmodell und dem uni-modalen Sprachverarbeitungsmodell, den Q-Former. Q-Former sind eine effiziente Methode, das Training von multimodalen Modellen durchzuführen. Wir diskutieren die Architektur, Vorteile, Nachteile und Wirkweisen.Support the show

Episode metadata supplied by the publisher feed · Published Jun 3, 2023

Embed this episode

Attribution link and audio player

NOW PLAYING

Episode 83 - Multimodale Modelle - Q-Former

0:00 28:08

1×

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Share this episode

Similar Episodes

No similar episodes found.

Similar Podcasts

No similar podcasts found.

Frequently Asked Questions

How long is this episode of Knowledge Science - Alles über KI, ML und NLP?

This episode is 28 minutes long.

When was this Knowledge Science - Alles über KI, ML und NLP episode published?

This episode was published on June 3, 2023.

Can I download this Knowledge Science - Alles über KI, ML und NLP episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.

URL copied to clipboard!