Uploaded June 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
------
CHAPTERS
0:00 Welcome: starting Chapter 5
1:55 Where we are in the book: Part 1 on perception
2:50 Recap of Chapters 3 and 4: approximating the posterior
8:33 Variational free energy as the quantity to minimize
10:28 Toward predictive coding: precision-weighted prediction errors
14:19 Discussion: sign conventions around equation 4.29
19:07 The delta (point-mass) approximation: keeping only the mean
22:56 The energy term and the MAP estimate (equation 5.4)
24:54 Gaussian likelihood and prior assumptions
27:47 Two prediction errors: sensory and prior
33:36 Precision as inverse variance
36:27 Prediction error as a signal, not a failure
38:24 Unit variances and the posterior mean in the figure
42:16 Precision weighting and confidence
45:11 Q&A: attention and trust in low-information settings
50:03 Examples: fog and darkness down-weight errors
54:52 Active inference in AI and how strong the assumptions are
56:52 Next time, and a note on maximum entropy priors
---
--- RESOURCES & TRANSCRIPT ---
đź“„ Full Transcript on GitHub:
github.com/ActiveInferenceInstitute/ActiveInferenceJournal/tree/main/data/video/activeinferenceinstitute/TextbookGroup/Namjoshi2026/Cohort_1/Session_020
Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/
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
------
CHAPTERS
0:00 Welcome: starting Chapter 5
1:55 Where we are in the book: Part 1 on perception
2:50 Recap of Chapters 3 and 4: approximating the posterior
8:33 Variational free energy as the quantity to minimize
10:28 Toward predictive coding: precision-weighted prediction errors
14:19 Discussion: sign conventions around equation 4.29
19:07 The delta (point-mass) approximation: keeping only the mean
22:56 The energy term and the MAP estimate (equation 5.4)
24:54 Gaussian likelihood and prior assumptions
27:47 Two prediction errors: sensory and prior
33:36 Precision as inverse variance
36:27 Prediction error as a signal, not a failure
38:24 Unit variances and the posterior mean in the figure
42:16 Precision weighting and confidence
45:11 Q&A: attention and trust in low-information settings
50:03 Examples: fog and darkness down-weight errors
54:52 Active inference in AI and how strong the assumptions are
56:52 Next time, and a note on maximum entropy priors
---
--- RESOURCES & TRANSCRIPT ---
đź“„ Full Transcript on GitHub:
github.com/ActiveInferenceInstitute/ActiveInferenceJournal/tree/main/data/video/activeinferenceinstitute/TextbookGroup/Namjoshi2026/Cohort_1/Session_020
Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/










