Uploaded October 2026 | Updated November 2026, 3 hours 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; finishing Chapter 10
1:30 Recap: categorical beliefs in discrete models
3:00 Planning over trajectories with expected free energy
4:30 Policy probabilities from negative expected free energy
6:00 10.1 Learning model parameters (A, B and D)
7:30 Initial-state beliefs and learned preferences
9:00 Recap: the two-armed bandit
10:30 Adding hierarchy to the model
12:00 The bandit in code: state factors and modalities
13:30 Multimodal representation of the bandit
16:30 10.14 Adding hierarchical depth
18:00 The visual grammar of Bayesian networks
21:00 Three-layer models
24:00 Hidden-state layers (Figure 10.18)
27:00 Nested time scales: an everyday example
28:30 Hierarchy in the brain
33:00 A hidden Markov model under a POMDP
34:30 Scene construction as a hierarchical model
37:30 Continuous, discrete and mixed (hybrid) models
40:30 The graphical brain
43:30 Observations at every level
45:00 Hierarchical bandit in code
49:30 Context probabilities and posterior slices
51:00 Inference at the slower time scale
54:00 Low-level policy selection
57:00 Discussion: separation of temporal scales
1:01:30 Deep active inference and scene construction code
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; finishing Chapter 10
1:30 Recap: categorical beliefs in discrete models
3:00 Planning over trajectories with expected free energy
4:30 Policy probabilities from negative expected free energy
6:00 10.1 Learning model parameters (A, B and D)
7:30 Initial-state beliefs and learned preferences
9:00 Recap: the two-armed bandit
10:30 Adding hierarchy to the model
12:00 The bandit in code: state factors and modalities
13:30 Multimodal representation of the bandit
16:30 10.14 Adding hierarchical depth
18:00 The visual grammar of Bayesian networks
21:00 Three-layer models
24:00 Hidden-state layers (Figure 10.18)
27:00 Nested time scales: an everyday example
28:30 Hierarchy in the brain
33:00 A hidden Markov model under a POMDP
34:30 Scene construction as a hierarchical model
37:30 Continuous, discrete and mixed (hybrid) models
40:30 The graphical brain
43:30 Observations at every level
45:00 Hierarchical bandit in code
49:30 Context probabilities and posterior slices
51:00 Inference at the slower time scale
54:00 Low-level policy selection
57:00 Discussion: separation of temporal scales
1:01:30 Deep active inference and scene construction code







