Signal-folding-based neuromorphic hardware for energy-efficient computing
Lei Ye
Nature Electronics, Published online: 27 April 2026; doi:10.1038/s41928-026-01626-z Two types of signal folding—for input signals and for weight conductance—can be implemented in molybdenum disulfide-based one-transistor–one-resistor arrays to decrease power consumption and improve weight precision in vector–matrix multiplication.