architecture-lifecycle-biology-geometry-economics

IN derived (depth 6)

Created 2026-06-21T10:27:01+00:00 · Reviewed 2026-06-21T15:37:01+00:00

ML architecture development follows a three-stage lifecycle with diminishing biological fidelity: biological neural systems catalyze initial designs through cross-pollination, data geometry filters for architectures with effective inductive biases, and hardware economics selects the survivors based on scalability — each successive stage further displacing the biological intuitions that seeded the design space.

Justifications

SL — The two-stage architecture filter (d5) preceded by biological catalysis (d5) reveals a complete three-phase causal chain

Antecedents (all must be IN):

  • IN architecture-selection-two-stage-filter — ML architecture selection operates as a two-stage filter: data geometry determines which inductive biases are effective (first filter), and hardware scalability determines which effective architectures survive (second filter) — scalability can veto geometric fit but not vice versa, explaining why theoretically superior architectures are routinely displaced.
  • IN biology-catalyzes-but-does-not-constrain-ml — Biological neural systems catalyzed ML's most important innovations by providing architectural intuitions through cross-pollination, but the field's greatest successes came from pragmatic departures from biological fidelity — the cross-pollination thesis holds for inspiration, not imitation.

Dependents

These beliefs depend on this one: