US20240046084A1 - Hadamard product implementation method and device, and storage medium - Google Patents

Hadamard product implementation method and device, and storage medium Download PDF

Info

Publication number
US20240046084A1
US20240046084A1 US18/267,431 US202118267431A US2024046084A1 US 20240046084 A1 US20240046084 A1 US 20240046084A1 US 202118267431 A US202118267431 A US 202118267431A US 2024046084 A1 US2024046084 A1 US 2024046084A1
Authority
US
United States
Prior art keywords
micro
ring
resonator
hadamard product
realizing
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US18/267,431
Other versions
US11893479B1 (en
Inventor
Jingjing Chen
Ruizhen WU
Ping Huang
Lin Wang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Wave Intelligent Technology Co Ltd
Original Assignee
Suzhou Wave Intelligent Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou Wave Intelligent Technology Co Ltd filed Critical Suzhou Wave Intelligent Technology Co Ltd
Assigned to INSPUR SUZHOU INTELLIGENT TECHNOLOGY CO., LTD. reassignment INSPUR SUZHOU INTELLIGENT TECHNOLOGY CO., LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HUANG, PING, CHEN, JINGJING, WANG, LIN, WU, Ruizhen
Application granted granted Critical
Publication of US11893479B1 publication Critical patent/US11893479B1/en
Publication of US20240046084A1 publication Critical patent/US20240046084A1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/067Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using optical means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/16Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization

Definitions

  • the present application relates to the technical field of photoelectric chips, and particularly relates to a method for realizing a Hadamard product, a device and a storage medium.
  • Photon calculation chips are the base and core of the modem electronic information industry. With the globalization and high-speed development of technology, the data volume required to be processed is sharply increasing, and the corresponding data processing models and algorithms are also continuously increasing, the result of which is the increasingly higher requirements on the calculation power and the power consumption. Photon calculation chips, by using photons as the information carrier, have the advantages of high-speed concurrency and a low power consumption, and thus is considered as the most promising solution for high-speed, high-data-volume and artificial intelligence calculation and processing in the future.
  • Optical Neural Networks Currently, the most commonly-used industrial solution of Optical Neural Networks (ONN) is to install exclusive devices. However, usually it is only suitable to solve the part of the multiplication and addition operation based on convolution operation. In Artificial Neural Networks (ANN), although the operation having the maximum volume is from the convolution operation, in networks such as Long Short-Term Memory (LSTM) artificial neural network, there also exists a large amount of operation of the Hadamard product.
  • LSTM Long Short-Term Memory
  • a purpose of the present application is to provide a method for realizing a Hadamard product, a device and a storage medium, which can utilize a micro-ring-resonator component to realize a simulated solution suitable for the Hadamard product in the optical neural network.
  • the particular solutions are as follows:
  • a method for realizing a Hadamard product comprising:
  • micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii;
  • the radii of the micro-ring-resonator groups are unequal.
  • the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one;
  • a quantity of the wavelengths of the to-be-treated optical signals is equal to a quantity of the micro-ring-resonator groups.
  • each of the micro-ring resonators comprises one straight waveguide and one micro-ring waveguide.
  • the straight waveguides of all of the micro-ring resonators of the micro-ring-resonator component are a same one shared straight waveguide;
  • the shared straight waveguide has an input port and a direct-passing port.
  • the radii of the micro-ring-resonator groups increase sequentially in a direction from the input port to the direct-passing port.
  • a transfer function between a light intensity at the direct-passing port and a light intensity at the input port is between 0 and 1.
  • the method further comprises:
  • An embodiment of the present application further provides a device for realizing a Hadamard product, wherein the device comprises a processor and a memory, and the processor, when executing a computer program stored in the memory, implements the above method for realizing a Hadamard product according to the embodiments of the present application.
  • An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is configured for storing a computer program, and the computer program, when executed by a processor, implements the above method for realizing a Hadamard product according to the embodiments of the present application.
  • the method for realizing a Hadamard product comprises: acquiring a plurality of to-be-treated optical signals with unequal wavelengths; inputting the to-be-treated optical signals into a wavelength division multiplexer; by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
  • the present application by using the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network. Furthermore, the present application further provides the device and the computer-readable storage medium corresponding to the method for realizing a Hadamard product, which further enables the method to have more practical applicability, and the device and the computer-readable storage medium have the corresponding advantages.
  • FIG. 1 is a flow chart of a method for realizing a Hadamard product according to an embodiment of the present application
  • FIG. 2 is a schematic diagram of the result of micro-ring resonators according to an embodiment of the present application
  • FIG. 3 is a light-intensity distribution diagram of the micro-ring resonators in a disresonance situation according to an embodiment of the present application
  • FIG. 4 is a light-intensity distribution diagram of the micro-ring resonators in a resonance situation according to an embodiment of the present application
  • FIG. 5 is a schematic diagram of the variation of the transfer functions of the micro-ring resonators with the phases according to an embodiment of the present application
  • FIG. 6 is a schematic structural diagram of a device for realizing a Hadamard product by using a wavelength division multiplexer and a micro-ring-resonator component according to an embodiment of the present application;
  • FIG. 7 is a block diagram showing a computing device for realizing a Hadamard product according the disclosure.
  • FIG. 8 is a block diagram showing storage unit for storing the program code for implementing the steps of the method according to the present disclosure.
  • the present application provides a method for realizing a Hadamard product. As shown in FIG. 1 , the method comprises the following steps:
  • WDM Wavelength Division Multiplexing
  • the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network.
  • the calculation mode is as follows:
  • the operation of the Hadamard product refers to multiplying the elements at the corresponding positions of two matrixes of the same order.
  • each of the micro-ring resonators MRR may comprise one straight waveguide and one micro-ring waveguide.
  • the MRRs are silicon-based MRRs of the All-pass type.
  • FIGS. 3 and 4 show the light-intensity distribution diagrams of the All-pass-type MRRs in the disresonance and resonance situations respectively.
  • the optical signal enters from the inputting end. If the wavelength of the incident light satisfies the resonance condition, most of the optical signal with that wavelength is restrained in the micro ring, and the outputting end has almost no output. If the resonance condition is not satisfied, the optical signal entering the micro ring has destructive interference, and the inputted optical waves are outputted directly from the direct-passing end. Therefore, the micro rings have the most basic function of filtering.
  • the resonance condition When light is being transmitted in the micro ring, it is restrained strongly by the micro ring. When it satisfies the condition that the optical path difference generated when it is transmitted around the micro ring by one round is an integral multiple m of the wavelength of the optical signal, resonance happens, and the intensity of the optical signal continuously increases.
  • the condition that enables it to have interaction and be intensified is referred to as the resonance condition.
  • the resonance equation of the micro ring is:
  • ⁇ i is the wavelength of the optical signal
  • m is an integral multiple of the wavelength of the optical signal
  • R is the radius of the MRR
  • n eff is the effective refractive index of the light.
  • T n ( ⁇ i ) a 2 - 2 ⁇ ra ⁇ cos ⁇ ( ⁇ i ) + r 2 1 - 2 ⁇ ra ⁇ cos ⁇ ( ⁇ i ) + ( ar ) 2 ( 3 )
  • ⁇ i is the phase of the MRR
  • r is a self-coupling coefficient
  • a defines the propagation loss of the ring and a directional coupler.
  • the value range of the transfer function is [0,1].
  • ⁇ i 4 ⁇ ⁇ 2 ⁇ R ⁇ n eff ⁇ i ( 5 )
  • FIG. 5 shows a diagram of the variation of the transfer function T n ( ⁇ i ) of the All-pass micro ring with the phase ⁇ i .
  • the radii of the micro-ring-resonator groups are unequal.
  • the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and the quantity of the wavelengths of the to-be-treated optical signals is equal to the quantity of the micro-ring-resonator groups.
  • a ⁇ B [a 1 b 1 a 2 b 2 a 3 b 3 ] (6)
  • FIG. 6 contains six MRRs, every two of which are one group of the equal radius, and the radii are R 1 , R 2 and R 3 .
  • the straight waveguides of all of the MRRs of the MRR component may be the same one shared straight waveguide.
  • the shared straight waveguide has an input port and a direct-passing port.
  • the transfer function between the light intensity at the direct-passing port and the light intensity at the input port is between 0 and 1.
  • the laser emits optical signals with the wavelengths of ⁇ 1 , ⁇ 2 and ⁇ 3 , and in order to facilitate the comprehension, it is assumed that all of the light intensities of the three optical signals are 1. Subsequently, they are fed to the MRR component via the WDM.
  • the MRR component is formed by three MRR groups with unequal radii. The radii are R 1 , R 2 and R 3 . The radii may increase sequentially in the direction from the input port to the direct-passing port, and satisfy:
  • T MRR 1 ( ⁇ 1 ) a 1
  • T MRR 2 ( ⁇ 2 ) b 1
  • T MRR 3 ( ⁇ 3 ) a 1
  • T MRR 4 ( ⁇ 4 ) b 2
  • T MRR 5 ( ⁇ 5 ) a 3
  • T MRR 6 ( ⁇ 6 ) b 3
  • the light intensities of the optical signals of 2 1 , 2 2 and 2 3 passing through the direct-passing end are T MRR 1 ( ⁇ 1 )T MRR 2 ( ⁇ 2 ), T MRR 3 ( ⁇ 3 )T MRR 4 ( ⁇ 4 ), and T MRR 5 ( ⁇ 5 )T MRR 6 ( ⁇ 6 ) respectively, i.e., a 1 b 1 , a 2 b 2 , a 3 b 3 , which is the result of the Hadamard product between A and B.
  • the method further comprises: controlling the transfer function between the light intensity at the direct-passing port and the light intensity at the input port to reach a target transfer function. Accordingly, by controlling the transfer function of the MRR component to be the target transfer function, it can be ensured that the magnitude of the applied electric current can accurately obtain the result of the required Hadamard product.
  • an embodiment of the present application further discloses a device for realizing a Hadamard product, wherein the device comprises a processor and a memory, and the processor, when executing a computer program stored in the memory, implements the method for realizing a Hadamard product according to the above embodiments.
  • the present application further discloses a computer-readable storage medium, wherein the computer-readable storage medium is configured for storing a computer program, and the computer program, when executed by a processor, implements the method for realizing a Hadamard product according to the above embodiments.
  • Each of devices according to the embodiments of the disclosure can be implemented by hardware, or implemented by software modules operating on one or more processors, or implemented by the combination thereof.
  • a person skilled in the art should understand that, in practice, a microprocessor or a digital signal processor (DSP) may be used to realize some or all of the functions of some or all of the modules in the device according to the embodiments of the disclosure.
  • the disclosure may further be implemented as device program (for example, computer program and computer program product) for executing some or all of the methods as described herein.
  • Such program for implementing the disclosure may be stored in the computer readable medium, or have a form of one or more signals. Such a signal may be downloaded from the internet websites, or be provided in carrier, or be provided in other manners.
  • FIG. 7 illustrates a block diagram of a computing device for executing the method according the disclosure.
  • the computing device includes a processor 1110 and a computer program product or a computer readable medium in form of a memory 1120 .
  • the memory 1120 could be electronic memories such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk or ROM.
  • the memory 1120 has a memory space 1130 for executing program codes 1131 of any steps in the above methods.
  • the memory space 1130 for program codes may include respective program codes 1131 for implementing the respective steps in the method as mentioned above. These program codes may be read from and/or be written into one or more computer program products.
  • These computer program products include program code carriers such as hard disk, compact disk (CD), memory card or floppy disk. These computer program products are usually the portable or stable memory cells as shown in reference FIG. 8 .
  • the memory cells may be provided with memory sections, memory spaces, etc., similar to the memory 1120 of the server as shown in FIG. 7 .
  • the program codes may be compressed for example in an appropriate form.
  • the memory cell includes computer readable codes 1131 ′ which can be read for example by processors 1110 . When these codes are operated on the server, the server may execute respective steps in the method as described above.
  • the steps of the method or algorithm described with reference to the embodiments disclosed herein may be implemented directly by using hardware, a software module executed by a processor or a combination thereof.
  • the software module may be embedded in a Random Access Memory (RAM), an internal memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or a storage medium in any other form well known in the art.
  • the method for realizing a Hadamard product comprises: acquiring a plurality of to-be-treated optical signals with unequal wavelengths; inputting the to-be-treated optical signals into a wavelength division multiplexer; by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
  • the present application further provides the device and the computer-readable storage medium corresponding to the method for realizing a Hadamard product, which further enables the method to have more practical applicability, and the device and the computer-readable storage medium have the corresponding advantages.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Neurology (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Optical Integrated Circuits (AREA)
  • Optical Modulation, Optical Deflection, Nonlinear Optics, Optical Demodulation, Optical Logic Elements (AREA)

Abstract

A method for realizing a Hadamard product, a device and a storage medium, includes: acquiring a plurality of to-be-treated optical signals with unequal wavelengths (S101); inputting the to-be-treated optical signals into a wavelength division multiplexer (S102); by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component includes a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii (S103); and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity (S104). Accordingly, by using the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network.

Description

  • The present application claims the priority of the Chinese patent application filed on Aug. 18, 2021 before the Chinese Patent Office with the application number of 202110945843.9 and the title of “HADAMARD PRODUCT IMPLEMENTATION METHOD AND DEVICE, AND STORAGE MEDIUM”, which is incorporated herein in its entirety by reference.
  • TECHNICAL FIELD
  • The present application relates to the technical field of photoelectric chips, and particularly relates to a method for realizing a Hadamard product, a device and a storage medium.
  • BACKGROUND
  • Chips are the base and core of the modem electronic information industry. With the globalization and high-speed development of technology, the data volume required to be processed is sharply increasing, and the corresponding data processing models and algorithms are also continuously increasing, the result of which is the increasingly higher requirements on the calculation power and the power consumption. Photon calculation chips, by using photons as the information carrier, have the advantages of high-speed concurrency and a low power consumption, and thus is considered as the most promising solution for high-speed, high-data-volume and artificial intelligence calculation and processing in the future.
  • Currently, the most commonly-used industrial solution of Optical Neural Networks (ONN) is to install exclusive devices. However, usually it is only suitable to solve the part of the multiplication and addition operation based on convolution operation. In Artificial Neural Networks (ANN), although the operation having the maximum volume is from the convolution operation, in networks such as Long Short-Term Memory (LSTM) artificial neural network, there also exists a large amount of operation of the Hadamard product.
  • SUMMARY
  • In view of the above, a purpose of the present application is to provide a method for realizing a Hadamard product, a device and a storage medium, which can utilize a micro-ring-resonator component to realize a simulated solution suitable for the Hadamard product in the optical neural network. The particular solutions are as follows:
  • A method for realizing a Hadamard product, comprising:
  • acquiring a plurality of to-be-treated optical signals with unequal wavelengths;
  • inputting the to-be-treated optical signals into a wavelength division multiplexer;
  • by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and
  • applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, the radii of the micro-ring-resonator groups are unequal.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and
  • a quantity of the wavelengths of the to-be-treated optical signals is equal to a quantity of the micro-ring-resonator groups.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, each of the micro-ring resonators comprises one straight waveguide and one micro-ring waveguide.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, the straight waveguides of all of the micro-ring resonators of the micro-ring-resonator component are a same one shared straight waveguide; and
  • the shared straight waveguide has an input port and a direct-passing port.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, the radii of the micro-ring-resonator groups increase sequentially in a direction from the input port to the direct-passing port.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, a transfer function between a light intensity at the direct-passing port and a light intensity at the input port is between 0 and 1.
  • In some embodiments, in the method for realizing a Hadamard product according to an embodiment of the present application, simultaneously with the step of applying the corresponding electric current to the micro-ring-resonator component, the method further comprises:
  • controlling the transfer function between the light intensity at the direct-passing port and the light intensity at the input port to reach a target transfer function.
  • An embodiment of the present application further provides a device for realizing a Hadamard product, wherein the device comprises a processor and a memory, and the processor, when executing a computer program stored in the memory, implements the above method for realizing a Hadamard product according to the embodiments of the present application.
  • An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium is configured for storing a computer program, and the computer program, when executed by a processor, implements the above method for realizing a Hadamard product according to the embodiments of the present application.
  • It can be seen from the above technical solutions that the method for realizing a Hadamard product according to the present application comprises: acquiring a plurality of to-be-treated optical signals with unequal wavelengths; inputting the to-be-treated optical signals into a wavelength division multiplexer; by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
  • In the present application, by using the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network. Furthermore, the present application further provides the device and the computer-readable storage medium corresponding to the method for realizing a Hadamard product, which further enables the method to have more practical applicability, and the device and the computer-readable storage medium have the corresponding advantages.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • In order to more clearly illustrate the technical solutions of the embodiments of the present application or the related art, the figures that are required to describe the embodiments or the related art will be briefly described below. Apparently, the figures that are described below are merely embodiments of the present application, and a person skilled in the art can obtain other figures according to the provided figures without paying creative work.
  • FIG. 1 is a flow chart of a method for realizing a Hadamard product according to an embodiment of the present application;
  • FIG. 2 is a schematic diagram of the result of micro-ring resonators according to an embodiment of the present application;
  • FIG. 3 is a light-intensity distribution diagram of the micro-ring resonators in a disresonance situation according to an embodiment of the present application;
  • FIG. 4 is a light-intensity distribution diagram of the micro-ring resonators in a resonance situation according to an embodiment of the present application;
  • FIG. 5 is a schematic diagram of the variation of the transfer functions of the micro-ring resonators with the phases according to an embodiment of the present application;
  • FIG. 6 is a schematic structural diagram of a device for realizing a Hadamard product by using a wavelength division multiplexer and a micro-ring-resonator component according to an embodiment of the present application;
  • FIG. 7 is a block diagram showing a computing device for realizing a Hadamard product according the disclosure; and
  • FIG. 8 is a block diagram showing storage unit for storing the program code for implementing the steps of the method according to the present disclosure.
  • DETAILED DESCRIPTION
  • The technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings of the embodiments of the present application. Apparently, the described embodiments are merely certain embodiments of the present application, rather than all of the embodiments. All of the other embodiments that a person skilled in the art obtains on the basis of the embodiments of the present application without paying creative work fall within the protection scope of the present application.
  • The present application provides a method for realizing a Hadamard product. As shown in FIG. 1 , the method comprises the following steps:
  • S101: acquiring a plurality of to-be-treated optical signals with unequal wavelengths;
  • S102: inputting the to-be-treated optical signals into a wavelength division multiplexer (Wavelength Division Multiplexing, WDM);
  • S103: by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and
  • S104: applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
  • In the method for realizing a Hadamard product according to an embodiment of the present application, by using the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network.
  • It should be noted that the Hadamard product is a matrix operation. It is defined that A, B ∈Cm×n, and A=[aij] and B=[bij], and the Hadamard product between A and B is expressed as A○B. The calculation mode is as follows:
  • A B = [ a 11 a 12 a 1 n a 21 a 22 a 2 n a m 1 a m 2 a mn ] [ b 11 b 12 b 1 n b 21 b 22 b 2 n b m 1 b m 2 b mn ] = [ a 11 b 11 a 12 b 12 a 1 n b 1 n a 21 b 21 a 22 b 22 a 2 n b 2 n a m 1 b m 1 a m 2 b m 2 a mn b mn ] ( 1 )
  • The operation of the Hadamard product refers to multiplying the elements at the corresponding positions of two matrixes of the same order.
  • In some embodiments, in a particular embodiment, in the method for realizing a Hadamard product according to an embodiment of the present application, as shown in FIG. 2 , each of the micro-ring resonators MRR may comprise one straight waveguide and one micro-ring waveguide. Preferably, the MRRs are silicon-based MRRs of the All-pass type. FIGS. 3 and 4 show the light-intensity distribution diagrams of the All-pass-type MRRs in the disresonance and resonance situations respectively. The optical signal enters from the inputting end. If the wavelength of the incident light satisfies the resonance condition, most of the optical signal with that wavelength is restrained in the micro ring, and the outputting end has almost no output. If the resonance condition is not satisfied, the optical signal entering the micro ring has destructive interference, and the inputted optical waves are outputted directly from the direct-passing end. Therefore, the micro rings have the most basic function of filtering.
  • When light is being transmitted in the micro ring, it is restrained strongly by the micro ring. When it satisfies the condition that the optical path difference generated when it is transmitted around the micro ring by one round is an integral multiple m of the wavelength of the optical signal, resonance happens, and the intensity of the optical signal continuously increases. The condition that enables it to have interaction and be intensified is referred to as the resonance condition. The resonance equation of the micro ring is:

  • 2πRn eff =mλ i  (2)
  • wherein λi is the wavelength of the optical signal, m is an integral multiple of the wavelength of the optical signal, R is the radius of the MRR, and neff is the effective refractive index of the light. The light with the wavelength satisfying the formula (2) satisfies the resonance condition, and is restrained in the micro ring. It can be known from the resonance equation (2) that the unequal wavelengths correspond to unequal micro-ring radii. When an electric current passes through the MRR, the MRR is heated, which results in the changing of the effective refractive index neff of the light, to cause the resonance wavelength to drift, whereby part of the light restrained in the micro ring is outputted from the direct-passing end.
  • The expression of the transfer function of the intensity of the light exiting from the through hole at the direct-passing end and the intensity of the light entering the input port of the all-pass resonator MRR is as follows:
  • T n ( ϕ i ) = a 2 - 2 ra cos ( ϕ i ) + r 2 1 - 2 ra cos ( ϕ i ) + ( ar ) 2 ( 3 )
  • wherein ϕi is the phase of the MRR, r is a self-coupling coefficient, and a defines the propagation loss of the ring and a directional coupler. The value range of the transfer function is [0,1].
  • If the amplitude of the inputted optical signal is Ein (the light intensity is |Ein|2), then the light intensity outputted from the MRR is:

  • |E out|2 =T ni)|E in|2  (4)
  • The expression of the phase ϕi in the formula (1) is:
  • ϕ i = 4 π 2 · R · n eff λ i ( 5 )
  • FIG. 5 shows a diagram of the variation of the transfer function Tni) of the All-pass micro ring with the phase ϕi.
  • When an electric current passes through the silicon-based MRR, the MRR is heated, which results in the changing of neff, which results in the changing of the phase ϕi, and finally influences the transfer function of the light intensity Tni). In other words, if the amplitude of the inputted optical signal is Ein (the light intensity is |Ein|2), by applying electric-current heating to the silicon-based micro ring, the transfer function Tni) is changed, thereby obtaining the wanted outputted light intensity |Eout|2. The present application realizes the calculation of the Hadamard product according to such a property of the silicon-based MRR.
  • In a particular embodiment, in the method for realizing a Hadamard product according to an embodiment of the present application, the radii of the micro-ring-resonator groups are unequal. Preferably, the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and the quantity of the wavelengths of the to-be-treated optical signals is equal to the quantity of the micro-ring-resonator groups.
  • In the following, taking A=[a1 a2 a3] and B=[b1 b2 b3] as an example, according to the definition, the Hadamard product between A and B is:

  • A○B=[a 1 b 1 a 2 b 2 a 3 b 3]  (6)
  • The present application realizes the calculation of the Hadamard product according to the property of the silicon-based MRR and the WDM. As shown in FIG. 6 , FIG. 6 contains six MRRs, every two of which are one group of the equal radius, and the radii are R1, R2 and R3.
  • In a particular embodiment, the straight waveguides of all of the MRRs of the MRR component may be the same one shared straight waveguide. The shared straight waveguide has an input port and a direct-passing port. The transfer function between the light intensity at the direct-passing port and the light intensity at the input port is between 0 and 1.
  • As shown in FIG. 6 , the laser emits optical signals with the wavelengths of λ1, λ2 and λ3, and in order to facilitate the comprehension, it is assumed that all of the light intensities of the three optical signals are 1. Subsequently, they are fed to the MRR component via the WDM. The MRR component is formed by three MRR groups with unequal radii. The radii are R1, R2 and R3. The radii may increase sequentially in the direction from the input port to the direct-passing port, and satisfy:

  • 2πR i n eff =mλ i i=1,2,3  (7)
  • It can be known from the formula (5) and the formula (7) that, if the MRRs are not heated, then all of the three optical signals with the wavelengths of λ1, λ2 and λ3 are restrained in the micro rings, and no optical signal is outputted at the direct-passing end. If the micro rings are individually applied with electric currents, the micro rings are heated, which results in the variation of neff, whereby the variation of the phase ϕi satisfies:

  • T MRR 1 1)=a 1 , T MRR 2 2)=b 1

  • T MRR 3 3)=a 1 , T MRR 4 4)=b 2

  • T MRR 5 5)=a 3 , T MRR 6 6)=b 3
  • In this case, the light intensities of the optical signals of 2 1 , 2 2 and 2 3 passing through the direct-passing end are TMRR 1 1)TMRR 2 2), TMRR 3 3)TMRR 4 4), and TMRR 5 5)TMRR 6 6) respectively, i.e., a1b1, a2b2, a3b3, which is the result of the Hadamard product between A and B.
  • In some embodiments, in a particular embodiment, in the method for realizing a Hadamard product according to an embodiment of the present application, simultaneously with the step of applying the corresponding electric current to the micro-ring-resonator component, the method further comprises: controlling the transfer function between the light intensity at the direct-passing port and the light intensity at the input port to reach a target transfer function. Accordingly, by controlling the transfer function of the MRR component to be the target transfer function, it can be ensured that the magnitude of the applied electric current can accurately obtain the result of the required Hadamard product.
  • Correspondingly, an embodiment of the present application further discloses a device for realizing a Hadamard product, wherein the device comprises a processor and a memory, and the processor, when executing a computer program stored in the memory, implements the method for realizing a Hadamard product according to the above embodiments.
  • The more particular process of the above-described method may refer to the corresponding contents disclosed in the above embodiments, which is not discussed further herein.
  • In some embodiments, the present application further discloses a computer-readable storage medium, wherein the computer-readable storage medium is configured for storing a computer program, and the computer program, when executed by a processor, implements the method for realizing a Hadamard product according to the above embodiments.
  • The more particular process of the above-described method may refer to the corresponding contents disclosed in the above embodiments, which is not discussed further herein.
  • The embodiments of the description are described in the mode of progression, each of the embodiments emphatically describes the differences from the other embodiments, and the same or similar parts of the embodiments may refer to each other. Regarding the device and the storage medium according to the embodiments, because they correspond to the methods according to the embodiments, they are described simply, and the relevant parts may refer to the description on the methods.
  • A person skilled in the art can further understand that the units and the algorithm steps of the examples described with reference to the embodiments disclosed herein may be implemented by using electronic hardware, computer software or a combination thereof. In order to clearly explain the interchangeability between the hardware and the software, the above description has described generally the configurations and the steps of the examples according to the functions. Whether those functions are executed by hardware or software depends on the particular applications and the design constraints of the technical solutions. A person skilled in the art may employ different methods to implement the described functions with respect to each of the particular applications, but the implementations should not be considered as extending beyond the scope of the present application.
  • Each of devices according to the embodiments of the disclosure can be implemented by hardware, or implemented by software modules operating on one or more processors, or implemented by the combination thereof. A person skilled in the art should understand that, in practice, a microprocessor or a digital signal processor (DSP) may be used to realize some or all of the functions of some or all of the modules in the device according to the embodiments of the disclosure. The disclosure may further be implemented as device program (for example, computer program and computer program product) for executing some or all of the methods as described herein. Such program for implementing the disclosure may be stored in the computer readable medium, or have a form of one or more signals. Such a signal may be downloaded from the internet websites, or be provided in carrier, or be provided in other manners.
  • For example, FIG. 7 illustrates a block diagram of a computing device for executing the method according the disclosure. Traditionally, the computing device includes a processor 1110 and a computer program product or a computer readable medium in form of a memory 1120. The memory 1120 could be electronic memories such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk or ROM. The memory 1120 has a memory space 1130 for executing program codes 1131 of any steps in the above methods. For example, the memory space 1130 for program codes may include respective program codes 1131 for implementing the respective steps in the method as mentioned above. These program codes may be read from and/or be written into one or more computer program products. These computer program products include program code carriers such as hard disk, compact disk (CD), memory card or floppy disk. These computer program products are usually the portable or stable memory cells as shown in reference FIG. 8 . The memory cells may be provided with memory sections, memory spaces, etc., similar to the memory 1120 of the server as shown in FIG. 7 . The program codes may be compressed for example in an appropriate form. Usually, the memory cell includes computer readable codes 1131′ which can be read for example by processors 1110. When these codes are operated on the server, the server may execute respective steps in the method as described above.
  • The steps of the method or algorithm described with reference to the embodiments disclosed herein may be implemented directly by using hardware, a software module executed by a processor or a combination thereof. The software module may be embedded in a Random Access Memory (RAM), an internal memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or a storage medium in any other form well known in the art.
  • In conclusion, the method for realizing a Hadamard product according to the embodiments of the present application comprises: acquiring a plurality of to-be-treated optical signals with unequal wavelengths; inputting the to-be-treated optical signals into a wavelength division multiplexer; by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity. Accordingly, by using the micro-ring resonators as the base for realizing the solution of an artificial neural network, using the wavelength division multiplexer to feed the to-be-treated optical signals to the micro-ring-resonator component, and heating by using the electric current, the effective refractive indexes and the phases of the micro-ring resonators can be changed, and the result of the Hadamard product can be obtained according to the light intensity of the outputted optical signal, thereby realizing a simulated solution suitable for the Hadamard product in the optical neural network. Furthermore, the present application further provides the device and the computer-readable storage medium corresponding to the method for realizing a Hadamard product, which further enables the method to have more practical applicability, and the device and the computer-readable storage medium have the corresponding advantages.
  • Finally, it should also be noted that, in the present text, relation terms such as first and second are merely intended to distinguish one entity or operation from another entity or operation, and that does not necessarily require or imply that those entities or operations have therebetween any such actual relation or order. Furthermore, the terms “include”, “comprise” or any variants thereof are intended to cover non-exclusive inclusions, so that processes, methods, articles or devices that include a series of elements do not only include those elements, but also include other elements that are not explicitly listed, or include the elements that are inherent to such processes, methods, articles or devices. Unless further limitation is set forth, an element defined by the wording “comprising a . . . ” does not exclude additional same element in the process, method, article or device comprising the element.
  • The method for realizing a Hadamard product, the device and the storage medium according to the present application have been described in detail above. The principle and the embodiments of the present application are described herein with reference to the particular examples, and the description of the above embodiments is merely intended to facilitate to comprehend the method according to the present application and its core concept. Moreover, for a person skilled in the art, according to the concept of the present application, the particular embodiments and the range of application may be varied. In conclusion, the contents of the description should not be understood as limiting the present application.

Claims (20)

1. A method for realizing a Hadamard product, comprising:
acquiring a plurality of to-be-treated optical signals with unequal wavelengths;
inputting the to-be-treated optical signals into a wavelength division multiplexer;
by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and
applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity;
wherein the radii of the micro-ring-resonator groups are unequal.
2. (canceled)
3. The method for realizing a Hadamard product according to claim 2, wherein the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and
a quantity of the wavelengths of the to-be-treated optical signals is equal to a quantity of the micro-ring-resonator groups.
4. The method for realizing a Hadamard product according to claim 3, wherein each of the micro-ring resonators comprises one straight waveguide and one micro-ring waveguide.
5. The method for realizing a Hadamard product according to claim 4, wherein the straight waveguides of all of the micro-ring resonators of the micro-ring-resonator component are a same one shared straight waveguide; and
the shared straight waveguide has an input port and a direct-passing port.
6. The method for realizing a Hadamard product according to claim 5, wherein the radii of the micro-ring-resonator groups increase sequentially in a direction from the input port to the direct-passing port.
7. The method for realizing a Hadamard product according to claim 6, wherein a transfer function between a light intensity at the direct-passing port and a light intensity at the input port is between 0 and 1.
8. The method for realizing a Hadamard product according to claim 7, wherein simultaneously with the step of applying the corresponding electric current to the micro-ring-resonator component, the method further comprises:
controlling the transfer function between the light intensity at the direct-passing port and the light intensity at the input port to reach a target transfer function.
9. A device for realizing a Hadamard product, wherein the device comprises a processor and a memory, and the processor, when executing a computer program stored in the memory, implements operations comprising:
acquiring a plurality of to-be-treated optical signals with unequal wavelengths;
inputting the to-be-treated optical signals into a wavelength division multiplexer;
by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and
applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity;
wherein the radii of the micro-ring-resonator groups are unequal.
10. A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is configured for storing a computer program, and the computer program, when executed by a processor, implements operations comprising:
acquiring a plurality of to-be-treated optical signals with unequal wavelengths;
inputting the to-be-treated optical signals into a wavelength division multiplexer;
by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component comprises a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and
applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity;
wherein the radii of the micro-ring-resonator groups are unequal.
11. The method for realizing a Hadamard product according to claim 1, wherein the micro-ring-resonator is a silicon-based micro-ring-resonator of an All-pass type.
12. (canceled)
13. The device for realizing a Hadamard product according to claim 12, wherein the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and
a quantity of the wavelengths of the to-be-treated optical signals is equal to a quantity of the micro-ring-resonator groups.
14. The device for realizing a Hadamard product according to claim 13, wherein each of the micro-ring resonators comprises one straight waveguide and one micro-ring waveguide.
15. The device for realizing a Hadamard product according to claim 14, wherein the straight waveguides of all of the micro-ring resonators of the micro-ring-resonator component are a same one shared straight waveguide; and
the shared straight waveguide has an input port and a direct-passing port.
16. The device for realizing a Hadamard product according to claim wherein the radii of the micro-ring-resonator groups increase sequentially in a direction from the input port to the direct-passing port.
17. The device for realizing a Hadamard product according to claim 16, wherein a transfer function between a light intensity at the direct-passing port and a light intensity at the input port is between 0 and 1.
18. The device for realizing a Hadamard product according to claim 17, wherein simultaneously with the step of applying the corresponding electric current to the micro-ring-resonator component, the method further comprises:
controlling the transfer function between the light intensity at the direct-passing port and the light intensity at the input port to reach a target transfer function.
19. (canceled)
20. The computer-readable storage medium according to claim 19, wherein the wavelengths of the to-be-treated optical signals correspond to the radii of the micro-ring-resonator groups one to one; and
a quantity of the wavelengths of the to-be-treated optical signals is equal to a quantity of the micro-ring-resonator groups.
US18/267,431 2021-08-18 2021-11-30 Hadamard product implementation method and device, and storage medium Active US11893479B1 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202110945843.9A CN113392965B (en) 2021-08-18 2021-08-18 Hadamard product realization method, device and storage medium
CN202110945843.9 2021-08-18
PCT/CN2021/134194 WO2023019799A1 (en) 2021-08-18 2021-11-30 Hadamard product implementation method and device, and storage medium

Publications (2)

Publication Number Publication Date
US11893479B1 US11893479B1 (en) 2024-02-06
US20240046084A1 true US20240046084A1 (en) 2024-02-08

Family

ID=77622824

Family Applications (1)

Application Number Title Priority Date Filing Date
US18/267,431 Active US11893479B1 (en) 2021-08-18 2021-11-30 Hadamard product implementation method and device, and storage medium

Country Status (3)

Country Link
US (1) US11893479B1 (en)
CN (1) CN113392965B (en)
WO (1) WO2023019799A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113392965B (en) 2021-08-18 2021-11-19 苏州浪潮智能科技有限公司 Hadamard product realization method, device and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8027587B1 (en) * 2007-08-21 2011-09-27 Sandia Corporation Integrated optic vector-matrix multiplier
US20120062974A1 (en) * 2009-03-20 2012-03-15 Cornell University Apparatus and methods for wide temperature range operation of micrometer-scale silicon electro-optic modulators
US20150024507A1 (en) * 2012-05-07 2015-01-22 Stc. Unm Biomarker sensing based on nanofluidic amplification and resonant optical detection
US20150268420A1 (en) * 2013-09-27 2015-09-24 Boe Technology Group Co., Ltd. Light transmitting substrate, array substrate, color filter substrate and display device
US20210264241A1 (en) * 2020-02-20 2021-08-26 Ohio University Optical multiply and accumulate unit
US20230152667A1 (en) * 2020-04-16 2023-05-18 The George Washington University Photonic tensor core matrix vector multiplier
US20230324607A1 (en) * 2020-08-31 2023-10-12 The Board Of Trustees Of The Leland Stanford Junior University Frequency-domain arbitrary linear transformations for photons

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109792297B (en) * 2016-10-18 2022-04-19 日本电信电话株式会社 Encoding device and decoding device
CN108616686B (en) * 2016-12-12 2020-09-11 南京理工大学 Full Hadamard matrix coding imaging method
CN109639359B (en) * 2019-01-07 2021-10-08 上海交通大学 Photonic neural network convolution layer chip based on micro-ring resonator
CN113031161B (en) * 2021-02-26 2022-09-13 北京邮电大学 Silicon-based microwave photon channelized chip
CN113392965B (en) * 2021-08-18 2021-11-19 苏州浪潮智能科技有限公司 Hadamard product realization method, device and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8027587B1 (en) * 2007-08-21 2011-09-27 Sandia Corporation Integrated optic vector-matrix multiplier
US20120062974A1 (en) * 2009-03-20 2012-03-15 Cornell University Apparatus and methods for wide temperature range operation of micrometer-scale silicon electro-optic modulators
US20150024507A1 (en) * 2012-05-07 2015-01-22 Stc. Unm Biomarker sensing based on nanofluidic amplification and resonant optical detection
US20150268420A1 (en) * 2013-09-27 2015-09-24 Boe Technology Group Co., Ltd. Light transmitting substrate, array substrate, color filter substrate and display device
US20210264241A1 (en) * 2020-02-20 2021-08-26 Ohio University Optical multiply and accumulate unit
US20230152667A1 (en) * 2020-04-16 2023-05-18 The George Washington University Photonic tensor core matrix vector multiplier
US20230324607A1 (en) * 2020-08-31 2023-10-12 The Board Of Trustees Of The Leland Stanford Junior University Frequency-domain arbitrary linear transformations for photons

Also Published As

Publication number Publication date
US11893479B1 (en) 2024-02-06
CN113392965B (en) 2021-11-19
WO2023019799A1 (en) 2023-02-23
CN113392965A (en) 2021-09-14

Similar Documents

Publication Publication Date Title
Tait et al. Demonstration of WDM weighted addition for principal component analysis
Shokraneh et al. The diamond mesh, a phase-error-and loss-tolerant field-programmable MZI-based optical processor for optical neural networks
Raymo et al. All-optical processing with molecular switches
Filipovich et al. Silicon photonic architecture for training deep neural networks with direct feedback alignment
US10627849B1 (en) Reservoir computing operations using multi-mode photonic integrated circuits
Tan et al. All-optical computation system for solving differential equations based on optical intensity differentiator
Li et al. Dilated convolutional neural networks for fiber Bragg grating signal demodulation
Cheng et al. A small microring array that performs large complex-valued matrix-vector multiplication
Huang et al. Programmable matrix operation with reconfigurable time-wavelength plane manipulation and dispersed time delay
US20240046084A1 (en) Hadamard product implementation method and device, and storage medium
CN113890620B (en) Silicon substrate photonic neural network based on tunable filter and modulation method thereof
Cheng et al. Photonic emulator for inverse design
Huang et al. Easily scalable photonic tensor core based on tunable units with single internal phase shifters
Li et al. All-optical image identification with programmable matrix transformation
US20240037382A1 (en) Method and device for implementing average pooling of neural network, and storage medium
Huang et al. Sophisticated deep learning with on-chip optical diffractive tensor processing
Sidick et al. Design and rigorous analysis of high-efficiency array generators
Williams et al. The multi-pulsing transition in mode-locked lasers: a low-dimensional approach using waveguide arrays
Fan et al. Photonic Hopfield neural network for the Ising problem
CN116739063A (en) Neural network accelerator based on multimode interferometer and coherent detection
CN113673677A (en) Method, equipment and medium for realizing nonlinear activation function RELU
Huang et al. Parallel photonic acceleration processor for matrix–matrix multiplication
Liu et al. Demonstration of an optical directed half-subtracter using integrated silicon photonic circuits
Zubac et al. Efficient uncertainty quantification of large two-dimensional optical systems with a parallelized stochastic Galerkin method
Hattori et al. Optical-electronic implementation of artificial neural network for ultrafast and accurate inference processing

Legal Events

Date Code Title Description
FEPP Fee payment procedure

Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

STCF Information on status: patent grant

Free format text: PATENTED CASE