ConceptAI & ML
Variational free energy
A quantity that serves as an upper bound on surprise or a lower bound on log evidence, incorporating a KL divergence between approximate and true posterior beliefs.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1Lectures that assume it
4Connections
12The lectures that define it or assume it, and the concepts next to it.
Concepts7
- KL divergence
- Probability density function
- Expected free energy
- Active inference
- Bayesian model reduction
- Epistemic value