Uploaded September 2026 | Updated November 2026, 2 days 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; from the Chapter 9 formalism to Chapter 10
3:00 10.1 notation and the worked examples
4:30 Dirichlet distributions (Appendix C)
7:30 Two pillars: learning parameters and learning what to sample
9:00 Recap: A and B matrices
10:30 Bayesian network notation
12:00 Factorized beliefs about parameters
13:30 Dirichlet priors over categorical parameters
16:30 Updating parameters of A and D
18:00 Learning the initial state (D)
19:30 The probability simplex
21:00 Beliefs converging to the true state
24:00 Example 10.1 in code
25:30 Example 10.3: two Dirichlet parameters
28:30 Discussion: pseudo-counts accumulate experience
34:30 Learning the observation likelihood (A)
37:30 Figure 10.4
40:30 Learning state transitions (B)
43:30 Action-conditioned B slices
46:30 Extensible code with a single null action
49:30 Discussion: time scales of learning
52:30 T-maze examples: information seeking
57:00 Aversive outcomes in the T-maze
58:30 Discussion: why novelty matters
1:01:30 Next: 10.2 habits, precision and policy optimization
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; from the Chapter 9 formalism to Chapter 10
3:00 10.1 notation and the worked examples
4:30 Dirichlet distributions (Appendix C)
7:30 Two pillars: learning parameters and learning what to sample
9:00 Recap: A and B matrices
10:30 Bayesian network notation
12:00 Factorized beliefs about parameters
13:30 Dirichlet priors over categorical parameters
16:30 Updating parameters of A and D
18:00 Learning the initial state (D)
19:30 The probability simplex
21:00 Beliefs converging to the true state
24:00 Example 10.1 in code
25:30 Example 10.3: two Dirichlet parameters
28:30 Discussion: pseudo-counts accumulate experience
34:30 Learning the observation likelihood (A)
37:30 Figure 10.4
40:30 Learning state transitions (B)
43:30 Action-conditioned B slices
46:30 Extensible code with a single null action
49:30 Discussion: time scales of learning
52:30 T-maze examples: information seeking
57:00 Aversive outcomes in the T-maze
58:30 Discussion: why novelty matters
1:01:30 Next: 10.2 habits, precision and policy optimization










