公开(公告)号：US20240232617A1

公开(公告)日：2024-07-11

申请号：US18394052

申请日：2023-12-22

Applicant: TSINGHUA UNIVERSITY

Inventor： Xing Lin ,  Zhengyang DUAN ,  Haiou ZHANG ,  Hang CHEN ,  Ziyang ZHENG ,  Hongkai XIONG

IPC: G06N3/08 ,  G06N3/067

CPC classification number: G06N3/08 ,  G06N3/067

Abstract: A dual adaptive training method of photonic neural networks (PNN), includes constructing, in a computer, a PNN numerical model including a PNN physical model and a systematic error prediction network model, where the PNN physical model is an error-free ideal PNN physical model of a PNN physical system, the systematic error prediction network model is an error model of the PNN physical system; determining measurement values of the PNN physical system and measurement values of the PNN numerical model, where the measurement values of the PNN physical system include final output values of the PNN physical system, and the measurement values of the PNN numerical model include final output values of the PNN numerical model; determining a similarity loss function based on comparison results between the measurement values of the PNN physical system and the measurement values of the PNN numerical model; determining a task loss function based on fused results of the measurement values of the PNN physical system and the measurement values of the PNN numerical model; and optimizing and updating parameters of the PNN numerical model based on the similarity loss function and the task loss function for in situ training of the PNN physical model.

公开(公告)号：US11600060B2

公开(公告)日：2023-03-07

申请号：US16893071

申请日：2020-06-04

Applicant: Tsinghua University

Inventor： Qionghai Dai ,  Tao Yan ,  Jiamin Wu ,  Xing Lin

IPC: G06V10/82 ,  G06N3/04 ,  G06N3/067 ,  G06N3/08 ,  G06T3/40

Abstract: The present disclosure discloses a nonlinear all-optical deep-learning system and method with multistage space-frequency domain modulation. The system includes an optical input module, configured to convert input information to optical information, a multistage space-frequency domain modulation module, configured to perform multistage space-frequency domain modulation on the optical information generated by the optical input module so as to generate modulated optical information, and an information acquisition module, configured to transform the modulated optical information onto a Fourier plane or an image plane, and to acquire the transformed optical information so as to generate processed optical information.

公开(公告)号：US09386296B2

公开(公告)日：2016-07-05

申请号：US14194931

申请日：2014-03-03

Applicant: Tsinghua University

Inventor： Qionghai Dai ,  Xing Lin ,  Jinli Suo

IPC: H04N13/00 ,  H04N13/02 ,  H04N5/335

CPC classification number: H04N13/207 ,  H04N5/335 ,  H04N13/271

Abstract: A method and an apparatus for coded focal stack photographing are provided. The method includes: changing a focal surface within a single exposure time and per-pixel coding a sensor readout for each focal surface to obtain a modulation function M(y,z), where y⊂{y1,y2} is a two-dimensional spatial coordinate and z is a depth coordinate of a latent three-dimensional focal stack F(y,z); coding the latent three-dimensional focal stack F(y,z) into a two-dimensional sensor image I(y) by using the modulation function M(y,z); and achieving one or more of a programmable non-planar focal surface imaging, an interleaved focal stack imaging, and a compressive focal stack imaging, based on the modulation functions M(y,z) and the two-dimensional sensor image I(y).

Abstract translation: 提供了一种用于编码焦点堆叠拍摄的方法和装置。 该方法包括：在单个曝光时间内改变焦点表面，并对每个焦面进行每像素编码传感器读数，以获得调制函数M（y，z），其中y⊂{y1，y2}是二维 空间坐标，z是潜在三维焦点堆栈F（y，z）的深度坐标; 通过使用调制函数M（y，z）将潜在三维焦点堆栈F（y，z）编码成二维传感器图像I（y）; 并且基于调制函数M（y，z）和二维传感器图像I（y）实现可编程非平面焦平面成像，交错焦点堆叠成像和压缩焦点堆叠成像中的一个或多个， 。