method
active
method:softmax-functionSoftmax Function
Neuronal dynamics computed from free energy gradients; interpreted as average firing rate of neural populations.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- PerceptionimplementsEquated with inference of past, present and future hidden states via minimization of variational free energy.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretation of neural implementation in Section 5.1.
- Using softmax to translate membrane potentials into firing rates, implementing lateral inhibition.
- Failure mode for output-surjectivity: LLMs may lack capacity to predict all tokens due to rank constraints
- Organisation that hosted the Holistic Intelligence unconference where the paper's ideas originated
- Selecting policies using a softmax (normalized exponential) function of negative expected free energy.
- Policies assigned probability via softmax of expected free energy; enables self-evidencing behavior.
- Implementation detail weighting softmax by log(n_memories) to prevent down-weighting of attention values as memory set grows.
- In RL, a scalar signal from the environment that defines the agent's goal; in active inference, reward is just another observation with associated preference.