A programmable diffractive deep neural network based on a digital-coding metasurface array
Che Liu,Qian Ma,Zhang Jie Luo,Qiao Ru Hong,Qiang Xiao,Hao Chi Zhang,Long Miao,Wen Ming Yu,Qiang Cheng,Lin Li,Tie Jun Cui +10 more
TLDR
In this paper , a programmable diffractive deep neural network based on a multi-layer digital-coding metasurface array is presented, which can handle various deep learning tasks for wave sensing, including image classification, mobile communication coding-decoding and real-time multi-beam focusing.Abstract:
The development of artificial intelligence is typically focused on computer algorithms and integrated circuits. Recently, all-optical diffractive deep neural networks have been created that are based on passive structures and can perform complicated functions designed by computer-based neural networks. However, once a passive diffractive deep neural network architecture is fabricated, its function is fixed. Here we report a programmable diffractive deep neural network that is based on a multi-layer digital-coding metasurface array. Each meta-atom on the metasurfaces is integrated with two amplifier chips and acts an active artificial neuron, providing a dynamic modulation range of 35 dB (from −22 dB to 13 dB). We show that the system, which we term a programmable artificial intelligence machine, can handle various deep learning tasks for wave sensing, including image classification, mobile communication coding–decoding and real-time multi-beam focusing. We also develop a reinforcement learning algorithm for on-site learning and a discrete optimization algorithm for digital coding. Using a multi-layer metasurface array in which each meta-atom of the metasurface acts as an active artificial neuron, a programmable diffractive deep neural network can be created that directly processes electromagnetic waves in free space for wave sensing and wireless communications. read more
Citations
More filters
Journal ArticleDOI
Touch-Programmable Metasurface for Various Electromagnetic Manipulations and Encryptions.
TL;DR: A touch-programmable metasurface based on touch sensing modules is proposed to realize various electromagnetic manipulations and encryptions and will have wide application prospects in imaging displays, wireless communications, and EM information encryptions.
Journal ArticleDOI
An All-In-One Multifunctional Touch Sensor with Carbon-Based Gradient Resistance Elements
TL;DR: Li et al. as mentioned in this paper proposed an all-in-one multipoint touch sensor (AIOM touch sensor) with only two electrodes, which can be used to recognize, learn, and memorize human-machine interactions.
Journal ArticleDOI
An All-In-One Multifunctional Touch Sensor with Carbon-Based Gradient Resistance Elements
TL;DR: Li et al. as discussed by the authors proposed an all-in-one multipoint touch sensor (AIOM touch sensor) with only two electrodes, which can be used to recognize, learn, and memorize human-machine interactions.
Journal ArticleDOI
Electrically addressable integrated intelligent terahertz metasurface
Benwen Chen,Xinru Wang,Weili Li,Chun Li,Zhaosong Wang,Hangbin Guo,Jingbo Wu,Kebin Fan,Caihong Zhang,Yunbin He,Biaobing Jin,Jian Chen,Peiheng Wu +12 more
TL;DR: An integrated self-adaptive metasurface (SAM) with THz wave detection and modulation capabilities based on the phase change material is developed, showing vast potential in eliminating coverage dead zones and other applications in THz communication.
Journal ArticleDOI
Highly integrated programmable metasurface for multifunctions in reflections and transmissions
TL;DR: This work designs a multi-channel switchable structure, dominated by a single-pole triple-throw switcher, to alternatively achieve the 1-bit reflection-phase programmable modulations, total reflection, absorption, and transmission, and the experimental results validate the capability of the proposed metasurface.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Journal ArticleDOI
Deep learning in neural networks
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
Journal ArticleDOI
Robust Face Recognition via Sparse Representation
TL;DR: This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.