❤️ Become The AI Epiphany Patreon ❤️ ► [ Ссылка ]
In this video I cover VQ-VAEs papers:
1) Neural Discrete Representation Learning
2) Generating Diverse High-Fidelity Images with VQ-VAE-2 (the only difference is the existence of a hierarchical structure of latents and priors)
Many novel interesting AI papers such as DALL-E and Jukebox from OpenAI as well as VQ-GAN build off of VQ-VAEs, so it's fairly important to have a good grasp of how they work.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ VQ-VAE1 paper: [ Ссылка ]
✅ VQ-VAE2 paper: [ Ссылка ]
✅ PyTorch code: [ Ссылка ]
✅ ELBO explained: [ Ссылка ]
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro
01:10 A tangent on autoencoders and VAEs
07:50 Motivation behind discrete representations
08:25 High-level explanation of VQ-VAE framework
11:20 Diving deeper
13:05 VQ-VAE loss
16:20 PyTorch implementation
23:30 KL term missing
25:50 Prior autoregressive models
28:50 Results
32:20 VQ-VAE two
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 ► [ Ссылка ]
One-time donation:
[ Ссылка ]
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
LinkedIn ► [ Ссылка ]
Twitter ► [ Ссылка ]
Instagram ► [ Ссылка ]
Facebook ► [ Ссылка ]
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► [ Ссылка ]
📢 SUBSCRIBE TO MY MONTHLY AI NEWSLETTER:
Substack ► [ Ссылка ]
💻 FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► [ Ссылка ]
📚 FOLLOW ME ON MEDIUM:
Medium ► [ Ссылка ]
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#vqvae #discretelatents #generativemodeling
![](https://i.ytimg.com/vi/VZFVUrYcig0/maxresdefault.jpg)