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

In deiner App anhören

Folgen

52 Folgen

  1. Reinforcement Learning: Training and Testing 28:37
  2. ChatGPT Is a Dead End 16:30
  3. Reinforcement Learning: Deep Policy Network 16:31
  4. DALL-E 2 is… meh 22:47
  5. GPT-4: What, Why, How? 43:56
  6. Reinforcement Learning Cartpole Intro 14:16
  7. Learning Fast with No Goals - VISR Explained 43:33
  8. Q Learning Tutorial: Dueling Architecture 26:33
  9. Automating Research With GPT API [Livestream] 1:49:10
  10. Q Learning Tutorial: Double Architecture 20:47
  11. Neural Networks From Zero: TFLearn Introduction 12:50
  12. This Embodied LLM is... 40:34
  13. Neural Networks From Zero: Tensorflow Session 22:08
  14. Sparks of AGI: What to Know 28:30
  15. Intro to Reinforcement Learning Made Simple 21:07
  16. Neural Networks From Zero: Tensorflow Intro 22:35
  17. Training RL From YouTube Videos 39:32
  18. Chinchilla Explained: Compute-Optimal Massive Language Models 40:30
  19. Neural Networks From Zero: Custom Data 18:33
  20. GPT-4 Outperforms RL by Studying and Reasoning... 🤔 26:31
  21. Neural Networks From Zero: Backpropagation and Testing 17:57
  22. Google's New Model Learns College-Level Math 49:12
  23. I Talked with Rich Sutton 1:38:06
  24. Neural Networks From Zero: Gradient Descent 14:19
  25. Q Learning Tutorial: Testing and Visualizing 18:52
  26. How I Got My First Machine Learning Job (Without a Degree) 18:01
  27. Is AI Research On the Wrong Path? 13:38
  28. Reinforcement Learning Made Simple - Q-Values 22:30
  29. Reinforcement Learning Made Simple - Policy 19:27
  30. Reinforcement Learning Made Simple - The Goal 19:18
  31. This is What Limits Current LLMs 10:49
  32. Neural Networks From Zero: Forward Propogation 25:59
  33. Doing ML Research as a Graduate Student 23:03
  34. 2 Years of My Research Explained in 13 Minutes 18:35
  35. This AI Learns from YouTube! 27:34
  36. Neural Networks From Zero: How It Works 13:33
  37. The AI Scaling Problem 20:52
  38. 12 Steps to AGI 52:10
  39. Q Learning Tutorial: Training and Loss Function 29:11
  40. AI Learns to Kill Cows in Runescape 14:11
  41. What's New In Machine Learning? 50:57
  42. Reinforcement Learning Made Simple - Reward 21:39
  43. Learning Forever, Backprop Is Insufficient 34:13
  44. AGI is NOT coming soon 20:59
  45. Q Learning Tutorial: Training Loop 27:52
  46. Agent Learns to do Reinforcement Learning 32:30
  47. Q Learning Tutorial: Experience Replay 34:43
  48. The Bellman Equations Explained - RL Theory 18:44
  49. The Best of NeurIPS 2022 32:24
  50. Q Learning Tutorial: Deep Q Networks 23:02