OPTICAL ARTIFICIAL NEURAL NETWORK SMART CHIP AND MANUFACTURING METHOD

Title:

OPTICAL ARTIFICIAL NEURAL NETWORK SMART CHIP AND MANUFACTURING METHOD

Document Type and Number:

WIPO Patent Application WO/2022/166189

Kind Code:

A1

Abstract:

The present application provides an optical artificial neural network smart chip and a manufacturing method, comprising: taking an optical filter layer as an input layer and a linear layer of an artificial neural network; taking a filter effect of the optical filter layer on incident light as a connection weight between the input layer and the linear layer; taking a square detection response of an image sensor as a first non-linear activation function in a nonlinear layer of the artificial neural network; and taking a processor as a fully connected layer, a second non-linear activation function in the nonlinear layer, and an output layer of the artificial neural network. Therefore, the filter layer and the image sensor implement related functions of the input layer, the linear layer and the nonlinear activation function in the artificial neural network in a hardware manner, so that complex signal and algorithm processing corresponding to the input layer and the linear layer is not required to be performed subsequently when intelligent processing is performed; images, spectra, incident light angles, and incident light phase information at different points of a target object space are utilized, thereby more accurately implementing intelligent processing of a target object.

More Like This:

WO/2022/053474	SYSTEM AND METHOD FOR AVOIDING CATASTROPHIC FORGETTING IN AN ARTIFICIAL NEURAL NETWORK
WO/2021/026044	FRAMEWORK FOR LEARNING TO TRANSFER LEARN
WO/2024/060521	CALCULATION METHOD FOR SCHEDULABLE POTENTIAL OF ACTIVE LOADS, TERMINAL, AND STORAGE MEDIUM

Inventors:

CUI KAIYU (CN)
XIONG JIAN (CN)
YANG JIAWEI (CN)
HUANG YIDONG (CN)
ZHANG WEI (CN)
FENG XUE (CN)
LIU FANG (CN)

Application Number:

PCT/CN2021/115966

Publication Date:

August 11, 2022

Filing Date:

September 01, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

UNIV TSINGHUA (CN)

International Classes:

G06N3/04; G06N3/067

Foreign References:

CN111386538A	2020-07-07
CN112041857A	2020-12-04
CN111832721A	2020-10-27
US20190019100A1	2019-01-17
US20170351293A1	2017-12-07
US20200257958A1	2020-08-13

Other References:

SUN JIE, ZHAI HONGCHEN, ZHANG YANXIN, LIU YUE, TANG YILIANG: "Integrated Opto-electronic Hybrid Neural Network for Pattern Recognition Controlled by Single Microprocessor", ACTA SCIENTIARUM NATURALIUM UNIVERSITATIS NANKAIENSIS, vol. 33, no. 1, 30 March 2000 (2000-03-30), pages 106 - 109+118, XP055956148
SHEN YICHEN; HARRIS NICHOLAS C.; SKIRLO SCOTT; ENGLUND DIRK; SOLJACIC MARIN: "Deep learning with coherent nanophotonic circuits", 2017 IEEE PHOTONICS SOCIETY SUMMER TOPICAL MEETING SERIES (SUM), 10 July 2017 (2017-07-10), pages 189 - 190, XP033143799, DOI: 10.1109/PHOSST.2017.8012714

Attorney, Agent or Firm:

CN-KNOWHOW INTELLECTUAL PROPERTY AGENT LIMITED (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: OPTICAL ARTIFICIAL NEURAL NETWORK SMART CHIP, SMART PROCESSING DEVICE, AND MANUFACTURING METHOD

Next Patent: INTELLIGENT GROUND LOCK AND WORKING METHOD THEREFOR