AlphaGo - Mastering the game of Go with deep neural networks and tree search | RL Paper Explained
❤️ Become The AI Epiphany Patreon ❤️ ► https://www.patreon.com/theaiepiphany
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
In this video, I cover the seminal AlphaGo paper - the first system to beat a professional Go player in the game of Go.
A task previously considered beyond the reach of current AI systems and at least 10 years off into the future, but neural networks proved them wrong!
You'll learn about:
✔️All of the nitty-gritty details around AlphaGo
✔️How MTCS and other subcomponents work
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ AlphaGo movie: https://www.youtube.com/watch?v=WXuK6gekU1Y&ab_channel=DeepMind
✅ Karpathy on AlphaGo: https://medium.com/@karpathy/alphago-in-context-c47718cb95a5
✅ Silver on UCB algo: https://www.youtube.com/watch?v=sGuiWX07sKw&list=PLqYmG7hTraZBiG_XpjnPrSNw-1XQaM_gB&index=12&t=2370s&ab_channel=DeepMind
✅ MTCS explained: https://www.youtube.com/watch?v=UXW2yZndl7U
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro
00:37 Context behind the game of Go
04:10 High-level overview of components - SL policies
07:25 RL policy network
09:30 The value network
11:15 Going deeper
16:30 Details around value network
19:05 Understanding the search (MTCS)
27:10 Evaluation of AlphaGo
33:30 Older techniques
34:40 Even more detailed explanation of APV-MTCS
37:40 Virtual loss
41:00 Engineering
45:30 Neural networks and symmetries
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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! ❤️
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💡 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 ► https://www.linkedin.com/in/aleksagordic/
Twitter ► https://twitter.com/gordic_aleksa
Instagram ► https://www.instagram.com/aiepiphany/
Facebook ► https://www.facebook.com/aiepiphany/
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► https://discord.gg/peBrCpheKE
📢 SUBSCRIBE TO MY MONTHLY AI NEWSLETTER:
Substack ► https://aiepiphany.substack.com/
💻 FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► https://github.com/gordicaleksa
📚 FOLLOW ME ON MEDIUM:
Medium ► https://gordicaleksa.medium.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#alphago #deepmind #reinforcementlearning
Видео AlphaGo - Mastering the game of Go with deep neural networks and tree search | RL Paper Explained канала Aleksa Gordić - The AI Epiphany
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
In this video, I cover the seminal AlphaGo paper - the first system to beat a professional Go player in the game of Go.
A task previously considered beyond the reach of current AI systems and at least 10 years off into the future, but neural networks proved them wrong!
You'll learn about:
✔️All of the nitty-gritty details around AlphaGo
✔️How MTCS and other subcomponents work
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ AlphaGo movie: https://www.youtube.com/watch?v=WXuK6gekU1Y&ab_channel=DeepMind
✅ Karpathy on AlphaGo: https://medium.com/@karpathy/alphago-in-context-c47718cb95a5
✅ Silver on UCB algo: https://www.youtube.com/watch?v=sGuiWX07sKw&list=PLqYmG7hTraZBiG_XpjnPrSNw-1XQaM_gB&index=12&t=2370s&ab_channel=DeepMind
✅ MTCS explained: https://www.youtube.com/watch?v=UXW2yZndl7U
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Intro
00:37 Context behind the game of Go
04:10 High-level overview of components - SL policies
07:25 RL policy network
09:30 The value network
11:15 Going deeper
16:30 Details around value network
19:05 Understanding the search (MTCS)
27:10 Evaluation of AlphaGo
33:30 Older techniques
34:40 Even more detailed explanation of APV-MTCS
37:40 Virtual loss
41:00 Engineering
45:30 Neural networks and symmetries
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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! ❤️
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💡 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 ► https://www.linkedin.com/in/aleksagordic/
Twitter ► https://twitter.com/gordic_aleksa
Instagram ► https://www.instagram.com/aiepiphany/
Facebook ► https://www.facebook.com/aiepiphany/
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► https://discord.gg/peBrCpheKE
📢 SUBSCRIBE TO MY MONTHLY AI NEWSLETTER:
Substack ► https://aiepiphany.substack.com/
💻 FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► https://github.com/gordicaleksa
📚 FOLLOW ME ON MEDIUM:
Medium ► https://gordicaleksa.medium.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#alphago #deepmind #reinforcementlearning
Видео AlphaGo - Mastering the game of Go with deep neural networks and tree search | RL Paper Explained канала Aleksa Gordić - The AI Epiphany
Показать
Комментарии отсутствуют
Информация о видео
7 марта 2021 г. 23:11:54
00:51:24
Другие видео канала
10k subscribers | joining Google DeepMind, updates, AMADay 25: Open NLLB - filtering HBS (Pt 2)Fastformer: Additive Attention Can Be All You Need | Paper ExplainedDay 24: Open NLLB - back from China, analyzing spikes, preparing HBS run (Pt 2)Day 6: Meta NLLB - data filtering (Pt. 4)Day 24: Open NLLB - back from China, filtering HBS data (Pt 3)Day 14: Open NLLB - Eval of our first run (English, Turkish, Hindi) (Pt 2.)Day 4: Training 600M NLLB - data preps (Pt. 2)Day 6: Meta NLLB - data filtering (Pt. 3)DeepMind's Android RL Environment - AndroidEnvDay 20: Open NLLB - analyzing HBS data (Bosnian, Croatian) (Pt 2)Day 11: Open NLLB - FSDP, on-boarding as a new-joiner (Pt 3.)Hamel Husain - Building LLM Apps in ProductionDay 28: Open NLLB - debugging fuzzy dedup, training fasttext LID (Pt 3)Day 10: Open NLLB - evaluation data, filtering (Pt 3.)Day 7: Meta NLLB - analyzing the training script, Jais paper (Pt. 4)EleutherAI Pythia w/ Hailey SchoelkopfDay 18: Open NLLB - data loading document, GitHub tasks (Pt 1 cont.)DeepMind's TacticAI: an AI assistant for football tactics | Petar VeličkovićJarvis for Images! (demo) - run locally, no external APIsDay 15: Open NLLB - ALTI+, detecting hallucinations (Pt 2)