The C3 Cube label-free neural architecture achieved 100% accuracy (150/150) for arrhythmia detection on a synthetic ECG dataset, matching a supervised MLP baseline.
Does the C3 Cube neural architecture improve arrhythmia detection accuracy on synthetic ECG data compared to a supervised MLP baseline?
A novel biologically-inspired neural architecture achieved 100% accuracy in detecting arrhythmias on a synthetic ECG dataset without training or labels.
Absolute Event Rate: 100% vs 100%
We introduce C3 Cube, a biologically-inspired neural architecture achieving arrhythmia detection with zero training, zero labels, and zero backpropagation. Classification emerges from resonance: pathological ECG morphologies trigger propagating activity cascades across a 3×3×3 lattice of HyperNeurons, while normal rhythms remain below the resonance threshold. On a synthetic ECG dataset (MIT-BIH style, 5 classes, 750 samples), C3 Cube achieves 100% accuracy (150/150), matching a supervised MLP baseline requiring 500 training epochs. Full technical disclosure withheld pending provisional patent filing.
chems omari (Sun,) conducted a other in ECG Arrhythmia (n=750). C3 Cube (Label-Free Hyper Neural Network) vs. Supervised MLP baseline was evaluated on Arrhythmia detection accuracy. The C3 Cube label-free neural architecture achieved 100% accuracy (150/150) for arrhythmia detection on a synthetic ECG dataset, matching a supervised MLP baseline.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: