X
Xing Lin
Researcher at Tsinghua University
Publications - 65
Citations - 3613
Xing Lin is an academic researcher from Tsinghua University. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 15, co-authored 56 publications receiving 2203 citations. Previous affiliations of Xing Lin include University of California, Berkeley & University of California, Los Angeles.
Papers
More filters
Journal ArticleDOI
All-optical machine learning using diffractive deep neural networks
TL;DR: 3D-printed D2NNs are created that implement classification of images of handwritten digits and fashion products, as well as the function of an imaging lens at a terahertz spectrum.
Journal ArticleDOI
All-Optical Machine Learning Using Diffractive Deep Neural Networks
TL;DR: In this paper, an all-optical Diffractive Deep Neural Network (D2NN) architecture is proposed to learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively.
Journal ArticleDOI
Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
Tiankuang Zhou,Xing Lin,Jiamin Wu,Yitong Chen,Hao Xie,Yipeng Li,Jingtao Fan,Huaqiang Wu,Lu Fang,Qionghai Dai +9 more
TL;DR: This work proposes an optoelectronic reconfigurable computing paradigm by constructing a diffractive processing unit (DPU) that can efficiently support different neural networks and achieve a high model complexity with millions of neurons.
Journal ArticleDOI
Spatial-spectral encoded compressive hyperspectral imaging
TL;DR: This paper proposes a novel compressive hyperspectral (HS) imaging approach that allows for high-resolution HS images to be captured in a single image and demonstrates other applications for the over-complete HS dictionary and sparse coding techniques, including 3D HS images compression and denoising.
Journal ArticleDOI
Computational Snapshot Multispectral Cameras: Toward dynamic capture of the spectral world
TL;DR: In this paper, the spectral sensing coherence information between their sensing matrices and spectrum-specific bases learned from a large-scale multispectral image database is analyzed and compared by examining the efficiency of their sampling schemes.