GPT 3

Multimodal Few-Shot Learning with Frozen Language Models | Paper Explained



The AI Epiphany

❤️ Become The AI Epiphany Patreon ❤️ ► https://www.patreon.com/theaiepiphany

In this video I cover “Multimodal Few-Shot Learning with Frozen Language Models” from DeepMind. They introduce Frozen – which is able to handle both visual and textual inputs and shows good generalization capabilities to novel visual question answering datasets combined with fast binding mechanisms even though it was only trained on image captioning.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: https://arxiv.org/abs/2106.13884
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⌚️ Timetable:

00:00 Intro
02:20 GPT-3 and emerging few-shot properties
04:20 Training procedure for Frozen
07:45 Inference
10:15 Strong generalization?
11:55 Prompting mechanisms and the hardest task
13:25 Quantitative results
19:50 Outro

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 BECOME A PATREON OF THE AI EPIPHANY ❤️

If these videos, GitHub projects, and blogs help you,
consider helping me out by supporting me on Patreon!

The AI Epiphany ► https://www.patreon.com/theaiepiphany
One-time donation:
https://www.paypal.com/paypalme/theaiepiphany

Much love! ❤️

Huge thank you to these AI Epiphany patreons:
Eli Mahler
Petar Veličković
Zvonimir Sabljic

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

💡 The AI Epiphany is a channel dedicated to simplifying the field of AI using creative visualizations and in general, a stronger focus on geometrical and visual intuition, rather than the algebraic and numerical “intuition”.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
👋 CONNECT WITH ME ON SOCIAL
(I’m mostly active on LinkedIn and Twitter)
LinkedIn ► https://www.linkedin.com/in/aleksagordic/
Twitter ► https://twitter.com/gordic_aleksa
Medium ► https://gordicaleksa.medium.com/

Instagram ► https://www.instagram.com/aiepiphany/
Facebook ► https://www.facebook.com/aiepiphany/

FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► https://github.com/gordicaleksa
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

#frozen #deepmind #multimodal