Probabilistic Graphical Models, HMMs using PGMPY

on YouTube ↗01h 23m

" summary

Covers building and querying generative probabilistic models with the open source pgmpy library, showing how to enter CPDs, run variable elimination queries and do evidential reasoning on examples like a restaurant traffic model and fraud detection. Emphasizes that Bayesian networks and HMMs give uncertainty estimates from few samples (coin‑toss demos show variance shrinking as N increases), support structure and parameter learning from data, and let users generate synthetic examples; notebooks and code are on GitHub.

AI-written summary · about

" chapters (43)

1. 0:00Introduction
2. 2:02Scenario
3. 4:20Deep Neural Net
4. 5:54Real Business Problems
5. 9:03Mathematical Questions
6. 12:03Agenda
7. 13:53Ria Aggarwal
8. 15:09What is probability
9. 15:29What are random variables
10. 16:13What is the conditional probability
11. 17:07What is marginalization
12. 17:34Bayesian vs Markov
13. 18:33Examples
14. 21:02Bayesian Networks
15. 21:34Conditional Probability Distribution
16. 22:32Joint Distribution
17. 22:54Weather Outlook
18. 23:21Causal Reasoning
19. 25:06Flow of Influence
20. 27:23Active Trails
21. 27:52Independence
22. 29:37Markov
23. 30:02Independence Assumption
24. 30:24Dynamic Bayesian Networks
25. 31:04Hidden Markov Model
26. 31:47Plate Model
27. 32:18Plate Models
28. 32:54Markov Networks
29. 35:20Factors
30. 39:55Gibbs Distribution
31. 41:42Conditional Random Fields
32. 47:20Log Linear Models
33. 48:50Utility Functions
34. 50:00Exercises
35. 51:11GitHub
36. 51:57Notebooks
37. 52:31PGMPY Library
38. 52:41Building a Bayesian Model
39. 54:32Evidence
40. 55:27CPD
41. 56:52Variable Elimination
42. 58:46evidential reasoning
43. 59:24Bayesian inference

" related talks

• 31mIntroduction to Causal Inference using pgmpyAnkur Ankan · PyData Amsterdam 2024
• 18mFast Inference for Probabilistic Graphical ModelsJiantong Jiang, Zeyi Wen, Atif Mansoor, Ajmal Mian · USENIX ATC 2024
• 43mProbabilistic Programming in the Real WorldZach Anglin · PyData DC 2018
• 42mBayesian Non-parametric Models for Data Science using PyMC3Christopher Fonnesbeck · PyCon 2018
• 01h 30mMaking Gaussian Processes UsefulBill Engels, Chris Fonnesbeck · PyData Global 2024
• 01h 33mMastering Gaussian Processes with PyMCChristopher Fonnesbeck, Alexandre Andorra · PyData NYC 2024
• 01h 07mProbabilistic Programming and Readable ModelsFritz Obermeyer · PyData Yerevan 2022
• 01h 03mA Personal Viewpoint on Probabilistic ProgrammingDaniel Roy · Uncertainty in Computation 2016