A programmable diffractive deep neural network based on a digital-coding metasurface array

نویسندگان

چکیده

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 passive structures can perform complicated functions designed by computer-based networks. However, once a network architecture fabricated, its function fixed. Here we report programmable multi-layer digital-coding metasurface array. Each meta-atom the metasurfaces with two amplifier chips acts an active neuron, providing dynamic modulation range 35 dB (from −22 to 13 dB). We show system, which term machine, handle various learning tasks for wave sensing, including image classification, mobile communication coding–decoding real-time multi-beam focusing. also develop reinforcement algorithm on-site discrete optimization digital coding. Using array in each as be directly processes electromagnetic waves free space sensing wireless communications.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Field-programmable beam reconfiguring based on digitally-controlled coding metasurface

Digital phase shifters have been applied in traditional phased array antennas to realize beam steering. However, the phase shifter deals with the phase of the induced current; hence, it has to be in the path of each element of the antenna array, making the phased array antennas very expensive. Metamaterials and/or metasurfaces enable the direct modulation of electromagnetic waves by designing s...

متن کامل

A Neural Network Classifier Based on Coding Theory

The new neural network classifier we propose transforms the classification problem into the coding theory problem of decoding a noisy codeword. An input vector in the feature space is transformed into an internal representation which is a codeword in the code space, and then error correction decoded in this space to classify the input feature vector to its class. Two classes of codes which give...

متن کامل

Face Recognition based on Deep Neural Network

In modern life, we see more techniques of biometric features recognition have been used to our surrounding life, especially the applications in telephones and laptops. These biometric recognition techniques contain face recognition, fingerprint recognition and iris recognition. Our work focuses on the face recognition problem and uses a deep learning method, convolutional neural network, to sol...

متن کامل

Short term electric load prediction based on deep neural network and wavelet transform and input selection

Electricity demand forecasting is one of the most important factors in the planning, design, and operation of competitive electrical systems. However, most of the load forecasting methods are not accurate. Therefore, in order to increase the accuracy of the short-term electrical load forecast, this paper proposes a hybrid method for predicting electric load based on a deep neural network with a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Nature electronics

سال: 2022

ISSN: ['2520-1131']

DOI: https://doi.org/10.1038/s41928-022-00719-9