Gradient Descent on Free Energy

Optimization procedure for simultaneously updating action selection and perception; uses step size ζ (default 4).

Neighborhood — ranked by edge-count

concept

free energy
implements
Thermodynamic potential ΔF = ΔE − TΔS; domain walls form if ΔF < 0
Perception
implements
Equated with inference of past, present and future hidden states via minimization of variational free energy.

method

Gradient Descent on Variational Free Energy
related_to
Process by which neuronal dynamics minimize free energy; produces empirically observable neural phenomena.
Variational Free Energy Minimization
implements
Minimizing variational free energy for perceptual inference and learning of model parameters.
Softmax Activation Function as Neuronal Model
implements
Using softmax to translate membrane potentials into firing rates, implementing lateral inhibition.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Gradient Descentmethod0.840
Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data
Neuronal responses can be described as gradient descent on variational free energy.claim0.833
Central claim: gradient descent on free energy is a valid process-level description of neural activity.
Can neuronal responses be described as a gradient descent on variational free energy?question0.810
Central research question: whether process-level neural dynamics conform to free energy minimization.
"the fact that a gradient descent appears to be a valid description of neuronal activity means that variational free energy is a Lyapunov function for neuronal dynamics"concept0.787
Key theoretical result: gradient descent formulation validates free energy as fundamental principle.
Expected Free Energy Minimizationmethod0.780
Minimizing expected free energy for planning, decision-making, and action selection.
The flow of internal and active states can be described as a gradient descent on variational free energy.claim0.777
A formal result from the proof.
The dynamics of synaptic plasticity follow a descent on the gradient of variational free energy.claim0.777
Learning as free energy gradient descent, Section 8.
Gradient methodmethod0.772
Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.