Castuner

Edan Meyer

Edan Meyer

Edan Meyer talks about AI, machine learning and especially reinforcement learning, with educational episodes focused on interesting new research. Links: Personal Site: https://www.edanmeyer.com/ Twitter: https://twitter.com/ejmejm1

Ascoltalo nella tua app

Episodi

43 episodi

  1. Google's New Model Learns College-Level Math 49:12
  2. I Talked with Rich Sutton 1:38:06
  3. Neural Networks From Zero: Gradient Descent 14:19
  4. Q Learning Tutorial: Testing and Visualizing 18:52
  5. How I Got My First Machine Learning Job (Without a Degree) 18:01
  6. Why Computers Won't Make Themselves Smarter | The Singularity 27:02
  7. Is AI Research On the Wrong Path? 13:38
  8. Reinforcement Learning Made Simple - Q-Values 22:30
  9. Reinforcement Learning Made Simple - Policy 19:27
  10. Reinforcement Learning Made Simple - The Goal 19:18
  11. This is What Limits Current LLMs 10:49
  12. Neural Networks From Zero: Forward Propogation 25:59
  13. Doing ML Research as a Graduate Student 23:03
  14. 2 Years of My Research Explained in 13 Minutes 18:35
  15. This AI Learns from YouTube! 27:34
  16. Neural Networks From Zero: How It Works 13:33
  17. The AI Scaling Problem 20:52
  18. 12 Steps to AGI 52:10
  19. Q Learning Tutorial: Training and Loss Function 29:11
  20. AI Learns to Kill Cows in Runescape 14:11
  21. What's New In Machine Learning? 50:57
  22. Reinforcement Learning Made Simple - Reward 21:39
  23. Learning Forever, Backprop Is Insufficient 34:13
  24. AGI is NOT coming soon 20:59
  25. Q Learning Tutorial: Training Loop 27:52
  26. Agent Learns to do Reinforcement Learning 32:30
  27. Q Learning Tutorial: Experience Replay 34:43
  28. The Bellman Equations Explained - RL Theory 18:44
  29. The Best of NeurIPS 2022 32:24
  30. Q Learning Tutorial: Deep Q Networks 23:02
  31. Using ChatGPT to Write My PhD Apps 23:24
  32. Q Learning AI Explained 7:57
  33. Is Gato Really the Future of AI? 29:02
  34. Model Based RL Finally Works! 35:45
  35. Making an AI to Answer Our Questions! (Part 2) 21:35
  36. Stable Diffusion - What, Why, How? 1:01:52
  37. This Algorithm Could Make a GPT-4 Toaster Possible 47:06
  38. Making an AI to Answer Our Questions! (Part 1) 23:11
  39. RL Foundation Models Are Coming! 37:48
  40. Reinforcement Learning: Training and Testing 28:37
  41. ChatGPT Is a Dead End 16:30
  42. Reinforcement Learning: Deep Policy Network 16:31
  43. DALL-E 2 is… meh 22:47