Math4Wisdom

M4W spaces

Investigations

Tools

Topics

Questions

Other Notes

Explore

Topics

Active Inference

Structured Active Inference

Active Inference learning

⁠

Active Inference textbook⁠

⁠

Surprise⁠

— minimizing Surprise = Maximizing model evidence. Variational Free Energy is a bound on

Surprise⁠

Model as self? Self-evidencing. Model & Self.

The model can/does have a model.

What is a good model?

What is a (nasty)

Surprise⁠

⁠

https://pubmed.ncbi.nlm.nih.gov/37703703/⁠

⁠

Statistics absorbed many terms of cognitive science:

⁠

Surprise⁠

Belief (Bayesian)

Attention, Learning, Memory

.... And now those terms are getting re-laundered back into the statistics of cognition. These lineages are separating and re-fusing back together. They have shared ancestry & also recent differences & shared context.

How can/might

Synergetics⁠

come into the culture?

Organic chemistry → Bringing in the Hexagon, etc.

Looking “high tech” → Neurons, cells, collective behavior, Hexagons.

How to connect with AI, ChatGPT?

e.g. LLM as next-token predictor.

High Road — Opposites co-exist and are the same. Two some. Environment is the fatalist point of view, always going to be part of the environment.

⁠

Mnemonics & Memes

The Art of Memory by Francis A. Yates.

Cartesian Theater⁠

... a memory palace/parade.

Linus with his “Markov blanket”

⁠

cognitive security

Snoopy flies OODA loop:

⁠

the active inference process has a velocity, meaning likewise acceleration.

Variational Free Energy (”nasty surprises” suggests a faulty model):

⁠

Or is this a case of confirming evidence that one’s self image — of a model loser perhaps — is correct? Lucy’s model of Charlie Brown seems spot on.

Load content from www.math4wisdom.com?

Loading external content may reveal information to 3rd parties. Learn more

Allow

Want to print your doc?
This is not the way.

Try clicking the ⋯ next to your doc name or using a keyboard shortcut (

CtrlP

) instead.