biological-plausibility-inversely-correlated-with-pragmatic-adoption
IN derived (depth 12)
Created 2026-06-21T14:15:26+00:00 · Reviewed 2026-06-21T15:37:01+00:00
Unsupervised deep learning methods are considered more biologically plausible than backpropagation, yet pragmatism's filtering of biological inspiration tends to retain efficiency properties (local connectivity, weight sharing, gating) while discarding robustness properties (redundancy, homeostasis, graceful degradation) — suggesting that the most biologically faithful approaches may be among the least pragmatically favored, and that the biological inspirations most readily adopted are those that enhance capability rather than reliability.
Justifications
SL — Biological plausibility and pragmatic adoption pull in opposite directions — the more faithful the biological inspiration, the less pragmatic filtering retains it.
Antecedents (all must be IN):
- IN dl-unsupervised-more-biologically-plausible-than-backprop — Unsupervised deep learning methods (generative models, deep belief networks) are considered more biologically plausible than supervised backpropagation.
- IN pragmatism-filters-biological-robustness-retains-efficiency — Pragmatism's filtering of biological inspiration systematically retains efficiency properties (local connectivity, weight sharing, gating) while discarding robustness properties (redundancy, homeostasis, graceful degradation) — this asymmetric selection explains why biologically-inspired architectures achieve superhuman performance yet remain adversarially fragile: pragmatism is a filter that passes exactly the biological properties that create capability and blocks exactly those that would create reliability.
Dependents
These beliefs depend on this one:
- IN pragmatism-filter-uniform-across-biology-evaluation-economics — Pragmatism operates as a uniform selection filter across all ML dimensions — filtering biological inspiration to retain efficiency while discarding robustness, and independently filtering evaluation instruments to be sensitive to performance while deaf to reliability signals — revealing a single systematic distortion rather than domain-specific accidents.