arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.07122cs.NEcs.LGphysics.app-ph
收藏

基于深度学习的实时被动目标识别的Meta-神经网络

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

Nanjing University(南京大学);Huazhong University of Science and Technology(华中科技大学)

Jingkai Weng, Yujiang Ding, Chengbo Hu, Xue-feng Zhu, Bin Liang, Jing Yang, Jianchun Cheng

摘要:

深度学习最近在各个学科都取得了巨大的成功,但传统上需要耗时的计算机处理或大尺寸的衍射元件。在这里,我们从理论上提出并实验证明了一个纯被动的“元神经网络”的紧凑性和高分辨率的实时识别复杂的对象,通过分析声散射。我们证明了我们的元神经网络模仿标准的神经网络,尽管其占地面积小,由于其超材料单位细胞的独特能力,被称为“元神经元”,产生深亚波长分布的离散相移作为可学习的参数在训练过程中。由此产生的设备表现出“智能”来执行所需的任务,有可能解决当前在减小设备尺寸、成本和能耗与提高识别速度和准确性之间的权衡,这一点通过手写数字识别的示例来展示。我们的机制开辟了通往新的基于超材料的深度学习范例的道路,并使智能传感器等概念设备能够自动分析信号,对声学,光学和相关领域具有深远的影响。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑