Uploaded August 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; Chapter 9
1:30 Announcement: the Computational Psychiatry Course
4:30 Code resources: SPM and pymdp
7:30 Building on earlier chapters
9:00 From Gaussian to categorical distributions
12:00 Categorical probabilities: no ordering of states
16:30 Bayes theorem in the discrete case (Eqs. 1.2 vs. 9.7)
19:30 The observation model and state prior
21:00 Clamping an observation
22:30 Normalizing to probabilities
25:30 Hidden states that change over time
27:00 The generative model over time
28:30 Example: priors about the weather
31:30 The D vector and initial states
34:30 D across multiple trials
36:00 Example: learning a new game
37:30 Uniform initial priors
39:00 Graphical models and parameters
42:00 Composing A, B and D; hidden Markov models
43:30 Example: expectations about musical notes
45:00 From HMMs to POMDPs
46:30 Preferences over observations (C)
48:00 Example: an agent that does not want to be lifted by a wave
49:30 Preferred states vs. preferred observations
51:00 pymdp examples and tutorials
52:30 Hierarchical models later in the book
54:00 Separating agent and environment
55:30 Perception without action
57:00 Walking through the HMM: priors and time steps
1:00:00 Bayes rule with evidence at each time step
1:01:30 The weather changes over time: B
1:03:00 Example: is a source trustworthy
1:04:30 Linking observations and states with A
1:06:00 Sharp vs. spread-out distributions
1:07:30 Visualizing beliefs
1:09:00 Resources: pymdp, SPM and recorded talks
1:12:00 Wrap-up
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; Chapter 9
1:30 Announcement: the Computational Psychiatry Course
4:30 Code resources: SPM and pymdp
7:30 Building on earlier chapters
9:00 From Gaussian to categorical distributions
12:00 Categorical probabilities: no ordering of states
16:30 Bayes theorem in the discrete case (Eqs. 1.2 vs. 9.7)
19:30 The observation model and state prior
21:00 Clamping an observation
22:30 Normalizing to probabilities
25:30 Hidden states that change over time
27:00 The generative model over time
28:30 Example: priors about the weather
31:30 The D vector and initial states
34:30 D across multiple trials
36:00 Example: learning a new game
37:30 Uniform initial priors
39:00 Graphical models and parameters
42:00 Composing A, B and D; hidden Markov models
43:30 Example: expectations about musical notes
45:00 From HMMs to POMDPs
46:30 Preferences over observations (C)
48:00 Example: an agent that does not want to be lifted by a wave
49:30 Preferred states vs. preferred observations
51:00 pymdp examples and tutorials
52:30 Hierarchical models later in the book
54:00 Separating agent and environment
55:30 Perception without action
57:00 Walking through the HMM: priors and time steps
1:00:00 Bayes rule with evidence at each time step
1:01:30 The weather changes over time: B
1:03:00 Example: is a source trustworthy
1:04:30 Linking observations and states with A
1:06:00 Sharp vs. spread-out distributions
1:07:30 Visualizing beliefs
1:09:00 Resources: pymdp, SPM and recorded talks
1:12:00 Wrap-up










