Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition

TL;DR

This paper introduces a passive, compact meta-neural-network device that uses metamaterials to perform real-time acoustic object recognition, mimicking neural networks with high resolution and efficiency.

Contribution

The work presents the first experimental demonstration of a passive metamaterial-based neural network capable of real-time object recognition, combining small size with high performance.

Findings

Successfully recognized handwritten digits in real-time

Demonstrated deep-subwavelength phase control with meta-neurons

Achieved high-resolution acoustic recognition with a passive device

Abstract

Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements. Here we theoretically propose and experimentally demonstrate a purely-passive "meta-neural-network" with compactness and high-resolution for real-time recognizing complicated objects by analyzing acoustic scattering. We prove our meta-neural-network mimics standard neural network despite its small footprint, thanks to unique capability of its metamaterial unit cells, dubbed "meta-neurons", to produce deep-subwavelength-distribution of discrete phase shift as learnable parameters during training. The resulting device exhibits the "intelligence" to perform desired tasks with potential to address the current trade-off between reducing device's size, cost and energy consumption and increasing recognition speed and accuracy, showcased by an example of handwritten digit recognition. Our mechanism opens the route to new metamaterial-based deep-learning paradigms and enable conceptual devices such as smart transducers automatically analyzing signals, with far-reaching implications for acoustics, optics and related fields.