Uploaded August 2026 | Updated November 2026, 1 day ago
Book: Fundamentals of Active Inference
Principles, Algorithms, and Applications of the Free Energy Principle for Engineers, by Sanjeev V. Namjoshi https://mitpress.mit.edu/9780262050951/fundamentals-of-active-inference/
Register: http://textbook-group.activeinference.institute/
Code: github.com/ActiveInferenceInstitute/fundamentals
Playlist of Textbook Group: youtube.com/playlist?list=PLNm0u2n1IwdrpoTg-9l37YIBiDrrOzTw-
Direct link to group document: coda.io/d/_dZHp_UGhVZE/Meetings_su3ToqMp
------
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Welcome; first session on Chapter 9
1:30 From continuous models to discrete, game-like tasks
3:00 Plan: three weeks on Chapter 9
4:30 Chapter 9 as a watershed in the book
6:00 Notes for following the maths without the book
7:30 Partially observable Markov decision processes (POMDPs)
9:00 Discrete states: one place at a time
12:00 Controllable vs. observable parts of the state space
15:00 What to specify: observation likelihood and state prior
16:30 Example: four weather states
18:00 Categorical distributions
19:30 The likelihood as a table (A matrix)
22:30 One-hot encoded observations
24:00 Reading the A matrix: rows and columns
27:00 Computing the likelihood of an observation
30:00 Normalizing by the evidence
31:30 Exact Bayesian inference with categorical distributions
33:00 The prior over hidden states (Eq. 9.14)
34:30 How prior and observation shape the posterior
36:00 9.2 Dynamic hidden states
37:30 Bayes rule for dynamic states (Eq. 9.16)
40:30 State transitions as a categorical distribution (B)
43:30 The hidden Markov model diagram
45:00 Agent vs. environment in the diagram
46:30 Simulation: predicting the weather over time
48:00 Figure 9.11: the inference window
49:30 Tau: indexing future predictions
51:00 Prediction and postdiction
52:30 Notation discussion
55:30 The group questions page
57:00 Continuous vs. categorical hidden states
1:00:00 Wrap-up: next week 9.3 to 9.4
Book: Fundamentals of Active Inference
Principles, Algorithms, and Applications of the Free Energy Principle for Engineers, by Sanjeev V. Namjoshi https://mitpress.mit.edu/9780262050951/fundamentals-of-active-inference/
Register: http://textbook-group.activeinference.institute/
Code: github.com/ActiveInferenceInstitute/fundamentals
Playlist of Textbook Group: youtube.com/playlist?list=PLNm0u2n1IwdrpoTg-9l37YIBiDrrOzTw-
Direct link to group document: coda.io/d/_dZHp_UGhVZE/Meetings_su3ToqMp
------
Active Inference Institute information:
Website: https://activeinference.institute/
X: https://x.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: https://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Welcome; first session on Chapter 9
1:30 From continuous models to discrete, game-like tasks
3:00 Plan: three weeks on Chapter 9
4:30 Chapter 9 as a watershed in the book
6:00 Notes for following the maths without the book
7:30 Partially observable Markov decision processes (POMDPs)
9:00 Discrete states: one place at a time
12:00 Controllable vs. observable parts of the state space
15:00 What to specify: observation likelihood and state prior
16:30 Example: four weather states
18:00 Categorical distributions
19:30 The likelihood as a table (A matrix)
22:30 One-hot encoded observations
24:00 Reading the A matrix: rows and columns
27:00 Computing the likelihood of an observation
30:00 Normalizing by the evidence
31:30 Exact Bayesian inference with categorical distributions
33:00 The prior over hidden states (Eq. 9.14)
34:30 How prior and observation shape the posterior
36:00 9.2 Dynamic hidden states
37:30 Bayes rule for dynamic states (Eq. 9.16)
40:30 State transitions as a categorical distribution (B)
43:30 The hidden Markov model diagram
45:00 Agent vs. environment in the diagram
46:30 Simulation: predicting the weather over time
48:00 Figure 9.11: the inference window
49:30 Tau: indexing future predictions
51:00 Prediction and postdiction
52:30 Notation discussion
55:30 The group questions page
57:00 Continuous vs. categorical hidden states
1:00:00 Wrap-up: next week 9.3 to 9.4










