Optical neural network general operator model, architecture and system

Abstract

The present disclosure relates to the field of optical computing technology, and in particular to a general operator model, architecture, and system for optical neural networks. The model includes: a reconfigurable timing coding module for acquiring an input optical signal and performing timing coding on the input optical signal based on the timing coding parameters corresponding to the target optical computing task to obtain a time-interleaved signal; a reconfigurable linear optical computing module for performing optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task to obtain a calculated optical signal; and a reconfigurable nonlinear activation module for performing nonlinear activation on the calculated optical signal based on the nonlinear activation function corresponding to the target optical computing task to obtain and output an optical computing result signal. The present disclosure using the above-mentioned scheme can improve the flexibility and practicality of optical computing.

Description

Technical Field

[0001] The present disclosure relates to the field of optical computing technology, and in particular to a general operator model, architecture, and system for an optical neural network. Background Art

[0002] With the rapid development of artificial intelligence and scientific computing, the complexity and scale of computing needs are increasing. However, existing electronic computing technologies are constrained by Moore's Law, and their performance is gradually approaching saturation, making it difficult to effectively meet the increasingly stringent computing power and power consumption requirements of large-scale, complex algorithms. Light has inherent advantages in propagation, such as high throughput and low latency. Optical computing technology, which uses photons instead of electrons as computing carriers, is seen as the key to breaking through existing computing bottlenecks. Summary of the Invention

[0003] The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first objective of the present disclosure is to propose a universal operator model for optical neural networks to improve the flexibility and practicality of optical computing.

[0005] The second objective of the present disclosure is to propose a general operator architecture for optical neural networks.

[0006] The third objective of the present disclosure is to propose a universal operator system for optical neural networks.

[0007] To achieve the above objectives, the first embodiment of the present disclosure proposes a general operator model for an optical neural network, including:

[0008] A reconfigurable timing coding module is used to obtain an input optical signal and perform timing coding on the input optical signal based on a timing coding parameter corresponding to a target optical computing task to obtain a time-interleaved signal;

[0009] a reconfigurable linear optical computing module, configured to perform optical computing on the time-interleaved signal based on an optical computing matrix corresponding to the target optical computing task to obtain a calculated optical signal;

[0010] The reconfigurable nonlinear activation module is used to perform nonlinear activation on the calculated optical signal based on the nonlinear activation function corresponding to the target optical computing task, and obtain and output an optical computing result signal.

[0011] Optionally, the timing coding parameters include the number of split beams and the delay duration. The reconfigurable timing coding module is used to perform timing coding on the input optical signal based on the timing coding parameters corresponding to the target optical computing task to obtain a time-interleaved signal, specifically for:

[0012] Splitting the input optical signal based on the number of split beams to obtain multiple split beams;

[0013] Based on the delay duration, the split beams in the multiple split beams are delayed so that the delay between adjacent split beams is the duration corresponding to a data symbol in the input optical signal, thereby obtaining a time-interleaved signal, wherein the time-interleaved signal includes multiple time-interleaved sub-signals.

[0014] Optionally, when the reconfigurable timing coding module is used to split the input optical signal, it is specifically used to:

[0015] The beam splitter is controlled to split the input optical signal.

[0016] Optionally, the reconfigurable timing coding module is used to delay the split beams of the multiple split beams based on the delay duration, specifically to:

[0017] Selecting a first microring resonator subset corresponding to the number of split beams from the first microring resonator set, and determining a control voltage corresponding to each first microring resonator in the first microring resonator subset;

[0018] The split light is input to the first microring resonator subset to control the first microring resonator subset to delay the split light.

[0019] Optionally, the time-interleaved signal includes a plurality of time-interleaved sub-signals, and the reconfigurable linear optical computing module is configured to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task, and to obtain the calculated optical signal, specifically for:

[0020] In the process of performing optical calculation on the time-interleaved signal based on the optical calculation matrix corresponding to the target optical calculation task, the columns in the matrix correspond one-to-one to the time-interleaved sub-signals, the multiple time-interleaved sub-signals input at the same time are multiplied one-to-one with the row elements in the rows corresponding to the multiple time-interleaved sub-signals input at the same time, and the multiple products obtained after the multiplication are added to obtain the calculated optical signal.

[0021] Optionally, the reconfigurable linear optical computing module is configured to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task, and to obtain the calculated optical signal, specifically for:

[0022] Based on the target optical computing task, determining a coupling coefficient corresponding to each modulator in a modulator array to obtain an optical computing matrix corresponding to the target optical computing task, wherein the modulator is at least one of a Mach-Zehnder interferometer or a waveguide coupler;

[0023] The time-interleaved signal is input into the modulator array for optical calculation to obtain a calculated optical signal.

[0024] Optionally, the reconfigurable nonlinear activation module is configured to perform nonlinear activation on the calculated optical signal based on a nonlinear activation function corresponding to the target optical computing task to obtain and output an optical computing result signal, including:

[0025] Selecting a second microring resonator corresponding to the nonlinear activation function corresponding to the target optical computing task from the second microring resonator set to obtain a second microring resonator subset, and determining a control voltage corresponding to each second microring resonator in the second microring resonator subset;

[0026] The calculated optical signal is input to the second microring resonator set to control the second microring resonator set to perform nonlinear activation on the calculated optical signal, thereby obtaining and outputting an optical calculation result signal.

[0027] To achieve the above-mentioned purpose, the second embodiment of the present disclosure proposes a general optical neural network operator architecture, including: a data input module, the general optical neural network operator model shown in any one of the first aspects above, an acquisition module, and a control module; wherein,

[0028] The data input module is used to obtain input data and encode the input data into a one-dimensional time optical signal to obtain an input optical signal;

[0029] The control module is used to reconstruct the reconfigurable temporal coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module in the optical neural network general operator model based on the target optical computing task, so as to control the optical neural network general operator model to perform optical computing on the input optical signal based on the target optical computing task to obtain an optical computing result signal;

[0030] The acquisition module is used to acquire the optical calculation result signal.

[0031] Optionally, the control module is further configured to:

[0032] Control the working status of the data input module and the acquisition module.

[0033] To achieve the above-mentioned purpose, an embodiment of the third aspect of the present disclosure proposes an optical neural network general operator system, including: the optical neural network general operator architecture shown in any one of the aforementioned second aspects.

[0034] In summary, the general operator model, architecture, and system of the optical neural network provided by the present disclosure can execute specific optical computing tasks by reconfiguring the parameters in the reconfigurable timing coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module. This eliminates the need to design independent computing models for specific optical computing tasks, thereby improving the flexibility and practicality of optical computing.

[0035] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above and / or additional aspects and advantages of the present disclosure will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0037] Figure 1 A schematic diagram of the structure of a general operator model of an optical neural network provided in an embodiment of the present disclosure;

[0038] Figure 2 A schematic diagram illustrating the principle of a convolution operator implementation solution provided in an embodiment of the present disclosure;

[0039] Figure 3 A schematic diagram of the operation of a general operator model of an optical neural network provided by an embodiment of the present disclosure;

[0040] Figure 4 A schematic diagram of the structure of a general operator architecture for an optical neural network provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0041] The following describes in detail embodiments of the present disclosure, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.

[0042] In recent years, the application of neural networks in artificial intelligence has achieved tremendous success. However, traditional electronic computing faces performance bottlenecks when processing complex neural networks. Optical neural networks offer the advantages of high speed, high throughput, and low power consumption, providing a new approach for efficient neural network computing. However, current optical neural network technologies are mostly designed for specific tasks, performing specialized computing functions, such as diffractive optical neural networks designed for image classification.

[0043] Optical neural networks lacking universal operators have limitations in many aspects:

[0044] Low development efficiency: Different applications require customized operators, which makes the development process cumbersome and time-consuming, and hinders rapid iteration and deployment of new applications.

[0045] High cost: Designing operators specifically for each task increases R&D costs and resource consumption, which is not conducive to economic efficiency and large-scale promotion;

[0046] Unstable performance: A dedicated operator may perform well on a specific task, but its performance may fluctuate significantly when switching between different tasks, lacking stability and versatility.

[0047] Lack of standardization: The lack of universal operators makes it difficult to establish unified development and operation standards, affecting the interoperability and scalability of the system.

[0048] Difficult to maintain and upgrade: Maintaining multiple dedicated operator systems increases the complexity, and upgrades require adjustment one by one, which is labor-intensive and prone to errors.

[0049] In summary, the lack of universal operators for optical neural networks has seriously affected the flexibility and practicality of optical neural networks, and restricted their widespread promotion and development in practical applications.

[0050] The present disclosure is described in detail below with reference to specific embodiments.

[0051] Figure 1 This is a schematic diagram of the structure of a general operator model of an optical neural network provided by an embodiment of the present disclosure. Figure 1 As shown, the optical neural network general operator model includes:

[0052] A reconfigurable timing coding module is used to obtain an input optical signal and perform timing coding on the input optical signal based on a timing coding parameter corresponding to a target optical computing task to obtain a time-interleaved signal;

[0053] A reconfigurable linear optical computing module is used to perform optical computing on the time-interleaved signal based on an optical computing matrix corresponding to a target optical computing task to obtain a calculated optical signal;

[0054] The reconfigurable nonlinear activation module is used to perform nonlinear activation on the calculated optical signal based on the nonlinear activation function corresponding to the target optical computing task, and obtain and output the optical computing result signal.

[0055] According to some embodiments, the target optical computing task refers to an optical computing task that needs to be performed on the input optical signal. The target optical computing task does not specifically refer to a fixed task.

[0056] In some embodiments, the timing encoding parameters refer to parameters used when performing timing encoding on the input light signal according to the target light computing task.

[0057] In some embodiments, the time-interleaved signal refers to an optical signal obtained by performing time-series encoding on an input optical signal.

[0058] According to some embodiments, the optical computation matrix refers to a computation matrix used when performing optical computation on an input optical signal according to a target optical computation task.

[0059] In some embodiments, the calculated optical signal refers to an optical signal obtained after performing optical calculation on the input optical signal.

[0060] In some embodiments, the calculation method when performing optical calculation on the input optical signal includes but is not limited to matrix multiplication, convolution, etc.

[0061] According to some embodiments, the main function of the nonlinear activation function is to introduce nonlinear properties into the neural network of the optical neural network universal operator model, which enables the optical neural network universal operator model to learn and simulate complex data patterns and functions. Without a nonlinear activation function, no matter how many layers the neural network has, it is essentially still a linear regression model, which limits the expressive power and complexity of the network. The nonlinear activation function enables the neural network to perform nonlinear transformations, thereby solving problems that linear models cannot solve. For example, in classification problems, nonlinear activation functions can help neural networks divide data of different categories, even if the data are linearly inseparable in the original space. In addition, the nonlinear activation function can also simulate the transmission rules of human neurons, that is, signals are transmitted only under specific stimuli, which increases the biological interpretability of the network.

[0062] It should be noted that the general operator model of the optical neural network provided by the present disclosure can execute a specific optical computing task by reconstructing the parameters in the reconfigurable timing coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module. This eliminates the need to design an independent computing model for the specific optical computing task, thereby improving the flexibility and practicality of optical computing.

[0063] Optionally, the timing coding parameters include the number of split beams and the delay duration. The reconfigurable timing coding module is used to perform timing coding on the input optical signal based on the timing coding parameters corresponding to the target optical computing task. When the time-interleaved signal is obtained, it is specifically used to:

[0064] Based on the number of split beams, the input optical signal is split to obtain multiple split beams;

[0065] Based on the delay duration, the split beams in the multiple split beams are delayed so that the delay between adjacent split beams is the duration corresponding to a data symbol in the input optical signal, thereby obtaining a time-interleaved signal, wherein the time-interleaved signal includes multiple time-interleaved sub-signals.

[0066] According to some embodiments, the reconfigurable timing coding module may control a beam splitter or other beam splitting element to split the input optical signal.

[0067] In some embodiments, after the reconfigurable timing coding module obtains multiple split beams of light, it can copy them to multiple channels respectively, and delay the split beams input in different channels by different lengths, so that the delay between adjacent channels is ultimately equal to the duration of a data symbol in the input optical signal.

[0068] According to some embodiments, the reconfigurable timing coding module can utilize the group delay effect of microring resonators to implement delay operations. By adjusting the control voltage of the microring resonators and the number of microring resonators, different delay codes can be achieved. For example, by cascading multiple microring resonators, different degrees of delay can be achieved.

[0069] In other words, the reconfigurable timing encoding module is used to delay the split beams of the multiple split beams based on the delay duration. A first microring resonator subset corresponding to the number of split beams is selected from the first microring resonator set, and a control voltage corresponding to each first microring resonator in the first microring resonator subset is determined. The split beams are input to the first microring resonator subset to control the first microring resonator subset to delay the split beams. Therefore, the reliability and accuracy of the delay operation can be improved.

[0070] In some embodiments, the reconfigurable timing coding module may also utilize a spiral waveguide delay line to implement a delay operation on the split beam.

[0071] Optionally, the reconfigurable linear optical computing module is used to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task, and to obtain the calculated optical signal, specifically for:

[0072] In the process of performing optical calculation on the time-interleaved signal based on the optical calculation matrix corresponding to the target optical calculation task, the columns in the matrix correspond one-to-one to the time-interleaved sub-signals, and multiple time-interleaved sub-signals input at the same time are multiplied one-to-one with the row elements in the rows corresponding to the multiple time-interleaved sub-signals input at the same time, and the multiple products obtained after the multiplication are added to obtain the calculated optical signal.

[0073] It should be noted that Figure 2 This is a schematic diagram of the principle of a convolution operator implementation solution provided by the embodiment of the present disclosure. Figure 2 As shown in the figure, first, the input data channel is expanded by beam splitting operation; then, the input data temporal interleaving encoding is realized by delay operation; finally, multi-channel convolution is realized by linear matrix operation. Therefore, the universal operator model of optical neural network can use the time-space interleaving transformation method to realize the multi-channel convolution operator based on linear matrix operation.

[0074] In the process of realizing multi-channel convolution through linear matrix operation, by using the time-interleaved signal as a matrix operation operator or a convolution operation operator, multiple time-interleaved sub-signals input at the same time are multiplied one-to-one with the row elements in the rows corresponding to the multiple time-interleaved sub-signals input at the same time, so as to realize the convolution operation between each row element of the optical calculation matrix and the input optical signal.

[0075] According to some embodiments, the reconfigurable linear optical computing module is used to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task. When the calculated optical signal is obtained, the coupling coefficient corresponding to each modulator in the modulator array can be determined based on the target optical computing task to obtain the optical computing matrix corresponding to the target optical computing task; the time-interleaved signal is input into the modulator array for optical computing to obtain the calculated optical signal.

[0076] In some embodiments, the modulator array forms a matrix for multiplication operations, with the coupling coefficient provided by each modulator corresponding to each element in the optical computation matrix, also known as a matrix multiplication operator. Modulators include, but are not limited to, Mach–Zehnder interferometers (MZIs) and waveguide couplers. Tunable MZIs and waveguide couplers make the matrix multiplication operator in the optical computation matrix reconfigurable.

[0077] In the MZI array structure, each MZI has two input ports and two output ports, which can realize any 2×2 unitary matrix operation. The unitary transformation of dimension can be achieved by Therefore, the MZI array can realize any unitary matrix.

[0078] In the waveguide coupler array structure, the input waveguide and the output waveguide cross vertically. At each intersection, a curved waveguide is used to couple the light in the horizontal input waveguide to the vertical output waveguide. Each curved waveguide has a modulator to adjust its transmittance, thereby changing the coupling coefficient from the input waveguide to the output waveguide at each intersection.

[0079] Optionally, the reconfigurable nonlinear activation module is used to perform nonlinear activation on the calculated optical signal based on the nonlinear activation function corresponding to the target optical computing task, to obtain and output an optical computing result signal, including:

[0080] Selecting a second microring resonator corresponding to a nonlinear activation function corresponding to a target optical computing task from the second microring resonator set to obtain a second microring resonator subset, and determining a control voltage corresponding to each second microring resonator in the second microring resonator subset;

[0081] The calculated optical signal is input to the second microring resonator set to control the second microring resonator set to perform nonlinear activation on the calculated optical signal, thereby obtaining and outputting an optical calculation result signal.

[0082] It should be noted that the on-chip nonlinear activation function is realized by utilizing the Kerr effect and free-carrier dispersion effect of the microring resonator. Near the resonant wavelength of the microring resonator, both the Kerr effect and free-carrier dispersion cause phase changes that are related to optical power. The transmittance and phase transfer coefficient have a nonlinear response relationship with the input optical power, which can form a fast and dynamic all-optical nonlinear activation function.

[0083] In some embodiments, the complex light intensity in the microring resonator It can be expressed as:

[0084]

[0085] Where t is time; is the resonant frequency of the resonator The detuned frequency, is the incident light frequency; is the refractive index; It is the change in refractive index caused by the Kerr effect; It is the refractive index change caused by free carrier dispersion; is a linear loss; is the two-photon absorption loss; is the free carrier absorption loss; is the energy coupled into the resonator, is the coupling efficiency, is the input energy. Therefore, by adjusting the control voltage and number of the second microring resonator, a reconfigurable and diversified nonlinear activation function can be achieved.

[0086] Take a scenario as an example, Figure 3 The working diagram of a general operator model of an optical neural network provided by the embodiment of the present disclosure. Figure 3 As shown in the figure, first, reconfigurable timing coding is achieved through the group delay of the microring resonator; then, reconfigurable linear optical computing is achieved through the MZI array or waveguide coupler array; finally, reconfigurable nonlinear activation is achieved through the microring resonator. As a result, basic neural network operations such as matrix multiplication, convolution, and nonlinear activation functions can be efficiently performed, which is applicable to a variety of application scenarios and neural network structures without the need for separate design and optimization for each application.

[0087] In order to implement the above embodiments, the present disclosure also proposes a general operator architecture for optical neural networks.

[0088] like Figure 4 As shown, the optical neural network universal operator architecture includes: a data input module, the optical neural network universal operator model provided in the above embodiment, an acquisition module and a control module; wherein,

[0089] A data input module is used to obtain input data and encode the input data into a one-dimensional time optical signal to obtain an input optical signal;

[0090] A control module is used to reconfigure the reconfigurable temporal coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module in the optical neural network universal operator model based on the target optical computing task, so as to control the optical neural network universal operator model to perform optical computing on the input optical signal based on the target optical computing task to obtain an optical computing result signal;

[0091] The acquisition module is used to collect the optical calculation result signal.

[0092] Optionally, the data input module is used to obtain input data and encode the input data into a one-dimensional time optical signal. When the input optical signal is obtained, it is specifically used to:

[0093] The voltage of the electro-optic modulator is controlled by a high-speed arbitrary waveform generator to convert the input data into the intensity of the optical signal, thereby encoding the input data.

[0094] Optionally, when the acquisition module is used to acquire the optical calculation result signal, it is specifically used to:

[0095] Control the photoelectric detector to collect the light calculation result signal.

[0096] Optionally, the control module is used to reconstruct the reconfigurable temporal coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module in the optical neural network general operator model based on the target optical computing task, specifically for:

[0097] Different timing coding parameters are achieved by adjusting the control voltage of the first microring resonator in the reconfigurable timing coding module;

[0098] Changing the optical computing matrix or convolution kernel weight by adjusting the voltage of the modulator in the reconfigurable linear optical computing module;

[0099] Different nonlinear activation functions are achieved by adjusting the control voltage of the second microring resonator in the reconfigurable nonlinear activation module.

[0100] Optionally, the control module is further configured to:

[0101] Control the working status of the data input module and acquisition module.

[0102] In summary, the architecture provided in this embodiment, by adopting a universal operator model for optical neural networks, can provide a standardized platform for optical neural networks, can more easily perform performance optimization and function expansion, can better be compatible with existing computing systems and architectures, and reduce the complexity and cost of system integration.

[0103] In order to implement the above embodiments, the present disclosure also proposes an optical neural network general operator system, including: the optical neural network general operator architecture provided by the above embodiments.

[0104] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this disclosure are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0105] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0106] This disclosure contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0107] The acquisition, transmission, storage, use, and processing of data in the technical solution disclosed herein are in compliance with the relevant provisions of national laws and regulations.

[0108] It should be noted that in the embodiments of the present disclosure, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary and their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0109] In the descriptions of the aforementioned embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0110] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0111] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0112] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable media include: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0113] It should be understood that various parts of the present disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0114] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0115] In addition, the functional units in the various embodiments of the present disclosure may be integrated into a single processing module, each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0116] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. A person of ordinary skill in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A general operator model for optical neural networks, characterized in that: include: A reconfigurable timing coding module is used to obtain an input optical signal and perform timing coding on the input optical signal based on timing coding parameters corresponding to a target optical computing task to obtain a time-interleaved signal, wherein the timing coding parameters include the number of split beams and the delay duration; The reconfigurable timing coding module is configured to perform timing coding on the input optical signal based on the timing coding parameters corresponding to the target optical computing task to obtain a time-interleaved signal. Specifically, the module is configured to split the input optical signal based on the number of split beams to obtain multiple split beams; and delay the split beams in the multiple split beams based on the delay duration so that the delay between adjacent split beams is the duration corresponding to one data symbol in the input optical signal to obtain a time-interleaved signal, wherein the time-interleaved signal includes multiple time-interleaved sub-signals. The reconfigurable timing encoding module is used to delay the split beams of the multiple split beams based on the delay duration, specifically to select a first microring resonator subset corresponding to the number of split beams from the first microring resonator set, and determine a control voltage corresponding to each first microring resonator in the first microring resonator subset; input the split beams into the first microring resonator subset to control the first microring resonator subset to delay the split beams; a reconfigurable linear optical computing module, configured to perform optical computing on the time-interleaved signal based on an optical computing matrix corresponding to the target optical computing task to obtain a calculated optical signal; A reconfigurable nonlinear activation module is used to perform nonlinear activation on the calculated optical signal based on the nonlinear activation function corresponding to the target optical computing task, obtain and output an optical computing result signal, and is specifically used to select a second microring resonator corresponding to the nonlinear activation function corresponding to the target optical computing task from the second microring resonator set to obtain a second microring resonator subset, and determine a control voltage corresponding to each second microring resonator in the second microring resonator subset; input the calculated optical signal into the second microring resonator set to control the second microring resonator set to perform nonlinear activation on the calculated optical signal, and obtain and output an optical computing result signal.

2. The model according to claim 1, characterized in that When the reconfigurable timing coding module is used to split the input optical signal, it is specifically used to: The beam splitter is controlled to split the input optical signal.

3. The model according to claim 1, characterized in that The time-interleaved signal includes a plurality of time-interleaved sub-signals, and the reconfigurable linear optical computing module is configured to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task to obtain the calculated optical signal, specifically for: In the process of performing optical calculation on the time-interleaved signal based on the optical calculation matrix corresponding to the target optical calculation task, the columns in the matrix correspond one-to-one to the time-interleaved sub-signals, the multiple time-interleaved sub-signals input at the same time are multiplied one-to-one with the row elements in the rows corresponding to the multiple time-interleaved sub-signals input at the same time, and the multiple products obtained after the multiplication are added to obtain the calculated optical signal.

4. The model according to claim 3, characterized in that The reconfigurable linear optical computing module is configured to perform optical computing on the time-interleaved signal based on the optical computing matrix corresponding to the target optical computing task to obtain the calculated optical signal, specifically for: Based on the target optical computing task, determining a coupling coefficient corresponding to each modulator in a modulator array to obtain an optical computing matrix corresponding to the target optical computing task, wherein the modulator is at least one of a Mach-Zehnder interferometer or a waveguide coupler; The time-interleaved signal is input into the modulator array for optical calculation to obtain a calculated optical signal.

5. A general operator architecture for optical neural networks, characterized in that: include: A data input module, a general operator model of an optical neural network according to any one of claims 1 to 4, an acquisition module, and a control module; wherein, The data input module is used to obtain input data and encode the input data into a one-dimensional time optical signal to obtain an input optical signal; The control module is used to reconstruct the reconfigurable temporal coding module, the reconfigurable linear optical computing module, and the reconfigurable nonlinear activation module in the optical neural network general operator model based on the target optical computing task, so as to control the optical neural network general operator model to perform optical computing on the input optical signal based on the target optical computing task to obtain an optical computing result signal; The acquisition module is used to acquire the optical calculation result signal.

6. The architecture according to claim 5, characterized in that The control module is further configured to: Control the working status of the data input module and the acquisition module.

7. A general operator system for optical neural networks, characterized in that: include: At least one optical neural network universal operator architecture as described in any one of claims 5 to 6.

Images