Self-evidencing

The Flow of the system states (i,s,a) aims to maximize the likelihood of the interal states given the external states. It performs a maximum likelihood inference on themselves (Self-evidencing) - while simultaneously minimizing the complexity - the divergence between the external states given the internal states, and the ‘prior’ distribution over the external states (Inference).

---

$=\underset{\text{Inaccuracy}}{\underbrace{E_{p^{\ast }(e|i,s,a)}[-\ln p^{\ast }(i,s,a|e)]}}+\underset{\text{Complexity}}{\underbrace{D_{KL}[p\ast (e|i,s,a)\Vert p(e)]}}$ can be changed; is usally presented as:

---

Evidence

Supporting

Handle	Title	Summary of relevant evidence	Link
Millidge et al. 2021	A Mathematical Walkthrough and Discussion of the Free Energy Principle	p. 9

Counter

Handle	Title	Summary of relevant evidence	Link

---

Connections

Derivated by Marginal flow lemma derivation Self-evidencing is existing

Is tracked by Variational Inference

---

Metadata

---

Sentence

Derivation