method
active
method:l2-distance-fitness-metricL2 distance fitness metric
Quantitative measure of morphogenetic success: Euclidean distance between evolving embryo phenotype and target smiling-face pattern.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- MorphogenesisaboutProcess by which cellular collectives generate large-scale structure and form; presented as a collective intelligence problem.
Methods (1)
method
- Fitness function (l2-distance)related_tosame_asQuantitative metric of closeness of embryo to target pattern; d = (1/N²) Σ(E_ij - T_ij)² with exponential scaling d' = 9^d.
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.
- Mean number of nonzero features as sparsity metric, tracked as EMA.
- Alternative penalty that spreads features across layers and finds only shared features.
- Quantitative measure of how well an embryo matches the target pattern; used for selection.
- Metric measuring the mean MSE between self and other-referencing activations across all hidden MLP/attention layers
- Measures magnitude match / shrinkage.
- Metric introduced to quantify steering selectivity by comparing the area of target and off-target concept probes.
- Evaluation metrics for exact and near-verbatim memorization.
- Crude measure of excess explanation of p over constituent dimensions, summed across features.