physics-inductive-bias-breaks-pragmatism-filter

OUT derived (depth 12)

Created 2026-06-21T14:15:26+00:00

Physics-informed neural networks, by grounding architecture in fundamental physical laws rather than biological analogy or data geometry, would provide an inductive bias source that bypasses pragmatism's systematic filtering of robustness properties — PINNs' physical constraints enforce consistency guarantees that pragmatic selection cannot strip away because they are load-bearing for the model's function, not optional efficiency properties.

Justifications

SL — PINNs' physics constraints are load-bearing (cannot be pragmatically stripped) unlike biological robustness properties (optional, hence filtered), but only if crisis isn't constitutive of capability itself.

Antecedents (all must be IN):

IN pinns-demonstrate-physics-as-alternative-inductive-bias — Physics-Informed Neural Networks embed physical laws directly into neural architecture, illustrating that domain-specific physical constraints can serve as a source of inductive bias distinct from both biological inspiration and data geometry — suggesting that grounding architecture in fundamental physics may offer an alternative path to effective inductive bias, though whether this bypasses pragmatic scalability considerations remains an open question.
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.

Unless (any of these IN defeats this justification):

IN crisis-constitutive-of-capable-ml — ML's reliability crisis appears deeply connected to capable ML itself — deep learning's foundational mechanisms (weight sharing for geometry-matched compression, gradient flow for trainability) have been validated as mathematical necessities rather than design choices, and the crisis these mechanisms produce is both self-perpetuating and structurally unresolvable within ML's existing intellectual resources. This suggests that a reliability crisis may be a recurring structural feature of ML paradigms powerful enough to be useful, though the link between mathematical necessity of the mechanisms and inevitability of the crisis remains an inference rather than a proven entailment.