Sensing Intelligence as a Trainable Metamaterial Property
Researchers have introduced the concept of "sensing intelligence," proposing that a metamaterial's physical structure can be optimized to preprocess external stimuli. This approach allows a neural network to train its own physical body, improving the efficiency of signal interpretation. By using differentiable simulation, the body's geometry is optimized to reduce the sensing loss, leading to up to a fivefold increase in accuracy or a significant reduction in the need for electronic sensors. AI
IMPACT This research could lead to more efficient AI systems by offloading some signal processing to the physical structure of devices, reducing computational load.