method
active
method:infonce-lossInfoNCE Loss
One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation up to scaling
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Contrastive learningimplementsSupervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor
Concepts (1)
concept
- Pointwise Mutual Information Kernelassociated_withsupportsThe kernel that contrastive learners converge to; similarity equals PMI between observations
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.
- In machine learning, a function measuring the distance between current and desired output; analogous to stress.
- Loss function used in both experiments: sum of squared differences between predicted and target grid
- Loss computed using discrete binary gate outputs, used to verify convergence to true discrete circuit
- The deadening effect of modern processes that prevent people from acting according to their feeling for the whole, damaging the global whole.
- One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation
- Addressing disparity in loss magnitudes across tasks at the loss level
- Economic concept related to epistemic value in expected free energy; information needed to realize rewards