ORMAS: Neural Architectural Transparency Enables Autonomous Self-Correction

Abstract

The neural network black box is not an inherent property of deep learning—it is a mathematical consequence of global backpropagation, where a single entangled error signal ren- ders mid-training structural collapse invisible. We show that structurally isolating gradient chains to bounded 4-operation local paths transforms a standard neural network into a trans- parent, self-correcting system. Our protocol, ORMAS, extends backpropagation with a per-node local loss anchored through a capacity-constrained shared bottleneck and a health-gated self-correction mechanism that autonomously diagnoses and repairs structural pathologies in real time. Gradient conflicts between signals are resolved via PCGrad projection, and all continuous corrections satisfy a mean-centering conservation constraint, bounded by an Input-to-State Stability (ISS) conver- gence analysis under local strong convexity. The architecture natively emits five layers of causal telemetry—from system- level health to exact per-parameter attribution—as physical properties of the forward and backward pass, not post-hoc ap- proximations. Empirically, correction frequency decays from 4.2 to 0.05 per epoch as the network stabilizes, consistent with the predicted ISS bound. Across 383 controlled experiments on four architectures (FC-DAG, CNN, Fat CNN, ResNet-18), ORMAS matches standard baselines on clean data while limit- ing accuracy decay under 40% label noise to 2.5 percentage points versus 7.8 for standard training. Under catastrophic mid-training structural collapse, ORMAS autonomously re- covers to 80 3 ± 1 6% accuracy where parameter-matched baselines permanently collapse to 10 0% across all indepen- dent initializations. Under sequential task shift with no replay buffer or modularity constraint, the network self-organizes into partially factorized internal representations, achieving 58 8% mean zero-shot compositional accuracy on novel combinations versus 25% chance. These results establish architectural trans- parency as a structural prerequisite for autonomous robustness.