2026
CLM-AI-003618= NP-completeCOMPUTATIONAL BOUNDThe cited theorem establishes NP-complete under the recorded model.Source: Training a 3-node neural network is NP-complete — Three-node threshold-network training complexity ↗
PROVENFinding weights consistent with labeled examples is NP-complete even for the specified three-node network.
The question, scope, and sources behind this Registry record.
Under the recorded neural network theory model, establish NP-complete.
Current frontiers derived from accepted Claims.
The accepted equality closes this optimization result.
Assertions tied to evidence, attribution, and review.
The frontier as it changed over time.
Only accepted Claims matching the current specification contribute to the displayed bounds. Strict inequalities remain open; contradictory Claims require editorial review.
No accepted machine-checked reproductions are recorded for this Limit.
Limits Registry. LR-003618. Three-node threshold-network training complexity. 2026.