Loss Function

In machine learning, a function measuring the distance between current and desired output; analogous to stress.

Neighborhood — ranked by edge-count

framework

Supervised Learning
implements
Learning through physical changes in mechanical networks, as an example of learning outside neural systems.

concept

Stress
associated_with
Defined as discrepancy between current and optimal state; key driver of homeostatic action and intelligence across all systems.

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.

SOO Loss Functionmethod0.822
A loss function measuring the dissimilarity of latent model representations of self and other, minimized during fine-tuning
Functionconcept0.797
The practical, working aspect of a building; reinterpreted as the dynamic harmony of moving centers.
Reward Functionconcept0.778
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.
Hard Lossconcept0.754
Loss computed using discrete binary gate outputs, used to verify convergence to true discrete circuit
InfoNCE Lossmethod0.754
One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation up to scaling
Loss of feelingconcept0.750
The deadening effect of modern processes that prevent people from acting according to their feeling for the whole, damaging the global whole.
Squared Difference Lossmethod0.748
Loss function used in both experiments: sum of squared differences between predicted and target grid
loss-scale balancingconcept0.748
Addressing disparity in loss magnitudes across tasks at the loss level