Uploaded December 2025 | Updated November 2026, 3 hours ago
2025 ReviewStream
coda.io/d/_dTwB_SP81yq/Videos-in-2025_suLE7EuH
Active Inference Institute information:
Website: https://www.activeinference.institute/
Twitter: twitter.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Introduction: the 72 videos of 2025
1:30 Series overview
3:00 Quarterly roundtables
4:30 Open science and evaluation
6:00 Distributionally robust free energy
7:30 The ELBO and variational free energy
9:00 MathStreams: string diagrams and category theory
10:30 Textbook group
12:00 Active InferAnt streams
13:30 The 5th Applied Active Inference Symposium
15:00 Interfaces and user experience
16:30 Visual representations of active inference
18:00 Early 2025 GuestStreams
19:30 April GuestStreams
21:00 Looking back at older streams
22:30 A recurring guest's series
24:00 Biological and generative active inference
25:30 Large reviews and applications
27:00 Semantic information
28:30 Attention narrowing and cognitive rigidity
30:00 Neural networks and variational Bayes
31:30 Brain-like variational inference
33:00 Bayesian mechanics of economic choice
34:30 Energy-based transformers
36:00 Artificial spin ice and material substrates
37:30 Quantum active inference
39:00 Perceptual control theory and free energy
40:30 Closing
2025 ReviewStream
coda.io/d/_dTwB_SP81yq/Videos-in-2025_suLE7EuH
Active Inference Institute information:
Website: https://www.activeinference.institute/
Twitter: twitter.com/InferenceActive
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: youtube.com/c/ActiveInference
Active Inference Livestreams: https://video.activeinference.institute/
------
CHAPTERS
0:00 Introduction: the 72 videos of 2025
1:30 Series overview
3:00 Quarterly roundtables
4:30 Open science and evaluation
6:00 Distributionally robust free energy
7:30 The ELBO and variational free energy
9:00 MathStreams: string diagrams and category theory
10:30 Textbook group
12:00 Active InferAnt streams
13:30 The 5th Applied Active Inference Symposium
15:00 Interfaces and user experience
16:30 Visual representations of active inference
18:00 Early 2025 GuestStreams
19:30 April GuestStreams
21:00 Looking back at older streams
22:30 A recurring guest's series
24:00 Biological and generative active inference
25:30 Large reviews and applications
27:00 Semantic information
28:30 Attention narrowing and cognitive rigidity
30:00 Neural networks and variational Bayes
31:30 Brain-like variational inference
33:00 Bayesian mechanics of economic choice
34:30 Energy-based transformers
36:00 Artificial spin ice and material substrates
37:30 Quantum active inference
39:00 Perceptual control theory and free energy
40:30 Closing

![ActInf ModelStream 026.1: Closed-form predictive coding via hierarchical Gaussian filters, Baskakovs
Closed-form predictive coding via hierarchical Gaussian filters https://arxiv.org/abs/2605.20293
Aleksandrs Baskakovs, Sylvain Estebe, Kenneth Enevoldsen, Kristoffer Nielbo, Chris Mathys, Nicolas Legrand
Predictive coding (PC) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to date, it remains slower, and performance degrades sharply as network depth increases. We trace both problems to a single simplification: current PC networks fix the precision matrix to the identity, discarding precision-weighted prediction errors that the variational derivation requires to be fast, local, and Bayesian. We close this gap by expressing predictive coding networks as deep hierarchical Gaussian filters (HGFs) and restore precision-weighted message passing, yielding dynamic uncertainty estimates and Hebbian-compatible update rules at every layer. The resulting networks can simultaneously learn activations, weights, and precisions under a single free-energy objective, with no global error signal, and resolve inference without requiring iterations or automatic differentiation. On FashionMNIST, our solution approaches backpropagation in epoch-level wall-clock cost while converging in fewer epochs, and outperforms it on online, data efficiency, and concept-drift tasks. We thus establish that closed-form variational inference with online precision learning provides a tractable foundation for deep predictive coding networks, retaining biological and interpretative advantages, without requiring iterative relaxation or global error signals.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
Cite as: arXiv:2605.20293 [cs.LG]
(or arXiv:2605.20293v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.20293
[Submitted on 19 May 2026]
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: https://www.youtube.com/c/ActiveInference/
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/
CHAPTERS
0:00 Welcome and introductions
1:30 Talk outline
3:00 Background: training networks with backpropagation
6:00 Limits of backprop: offline learning and forgetting
9:00 Predictive coding and local learning rules
12:00 Prospective configuration
13:30 Analogy: reaching agreement in a network
18:00 Problems: slow inference and signal attenuation
19:30 Nodes as agents, not cogs
21:00 Precision and Bayesian belief updating
24:00 Injecting uncertainty over time
25:30 Hierarchical Gaussian filters: volatility coupling
27:00 From HGFs to predictive coding networks
28:30 Children send precision to parents
30:00 Precision-weighted learning and plasticity
31:30 Benchmarks vs. backprop and predictive coding networks
33:00 One inference pass in deep networks
34:30 Online and continual learning
36:00 Label-switching tasks
37:30 Summary: deep HGF networks
39:00 Future directions
40:30 Q&A
42:00 Q&A: batch vs. online learning
43:30 Q&A: time-series data
46:30 Q&A: depth and training time
49:30 Q&A: networks that choose their own update rules
52:30 Q&A: specifying the state space
55:30 Q&A: uncertainty for action
57:00 Q&A: optimizers in the benchmarks
58:30 Q&A: transformer architectures in the toolbox
1:01:30 Q&A: parameters per node
1:03:00 Q&A: interpretability
1:04:30 Q&A: applications and LLM agents
1:07:30 Closing thoughts ActInf ModelStream 026.1: Closed-form predictive coding via hierarchical Gaussian filters, Baskakovs](https://i.ytimg.com/vi/gcLQx0nAww0/mqdefault.jpg)








