CN116109854B - Military weapon equipment category determining method and device, medium and electronic device - Google Patents
Military weapon equipment category determining method and device, medium and electronic device Download PDFInfo
- Publication number
- CN116109854B CN116109854B CN202111319818.6A CN202111319818A CN116109854B CN 116109854 B CN116109854 B CN 116109854B CN 202111319818 A CN202111319818 A CN 202111319818A CN 116109854 B CN116109854 B CN 116109854B
- Authority
- CN
- China
- Prior art keywords
- quantum
- parameter
- sub
- value
- military
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims description 86
- 238000013528 artificial neural network Methods 0.000 claims description 69
- 239000002096 quantum dot Substances 0.000 claims description 27
- 230000006870 function Effects 0.000 claims description 23
- 238000013507 mapping Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 15
- 239000002356 single layer Substances 0.000 claims description 14
- 238000010586 diagram Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000010410 layer Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000021615 conjugation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008571 general function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/002—Image coding using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a device, a medium and an electronic device for determining the type of military weapons, which are used for carrying out quantum coding on an acquired military image to be identified through a quantum image coding algorithm, converting classical data into quantum input, then carrying out evolution and calculation on a target quantum state obtained through coding through a quantum and classical mixed convolution algorithm, and obtaining the type of the military weapons of a target object in the military image, thereby realizing the rapid determination of the type of the military weapons of the target object in the military image.
Description
Technical Field
The invention belongs to the technical field of quantum computing, and particularly relates to a method and a device for determining the type of military weapon equipment, a medium and an electronic device.
Background
Artificial intelligence is used as the most important subversion technology, is applied in the military field to become a main factor leading the new military revolution of the world, and is necessary to rewrite war rules in the future to promote the generation of intelligent war. The method uses artificial intelligence as a technical means to solve the key problem of target identification of related military weaponry in the battlefield, and is one of the important means for winning future intelligent wars.
In the classical neural network model, implicit features among pixels in an image are found through image convolution so as to identify, and the classical neural network model has a good effect in the field of computing base vision. The convolution of the image is a calculation with high complexity, the calculation speed of the classical neural network model is rapidly reduced along with the increase of the data volume, and the type of military weapon equipment is rapidly determined, so that the information support is provided for the military command decision, and the technical problem to be solved is solved.
Disclosure of Invention
The invention aims to provide a military weapon equipment category determining method, a military weapon equipment category determining device, a military weapon equipment category determining medium and an electronic device, which aim to rapidly determine the category of the military weapon equipment through quantum computation, thereby providing information support for military command decisions.
One embodiment of the present application provides a military weapon equipment category determination method, the method comprising:
Acquiring a military image to be identified;
carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
And performing evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm to obtain the military weapon equipment category of the target object in the military image.
Optionally, the quantum encoding the military image by a quantum image encoding algorithm to obtain a target quantum state includes:
obtaining a quantum bit, a single quantum logic gate RY containing a parameter and a single quantum logic gate RZ containing the parameter;
determining parameter values of the single quantum logic gate RY with the parameters and the single quantum logic gate RZ with the parameters based on pixel values of the military image, and sequentially adding the single quantum logic gate RY and the single quantum logic gate RZ after the parameter values are determined to the quantum bit to obtain a quantum image coding circuit;
And evolving an initial quantum state of the quantum bit to a target quantum state through the quantum image coding circuit.
Optionally, the determining parameter values of the single quantum logic gate RY with parameters and the single quantum logic gate RZ with parameters based on pixel values of the military image includes:
Taking the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum logic gate RY, and taking the square of the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum rotary logic gate RZ.
Optionally, the quantum and classical mixed convolution algorithm includes a quantum convolution neural network and a classical convolution neural network, and the performing evolution and calculation on the target quantum state by the quantum and classical mixed convolution algorithm to obtain a military weapon equipment category of the target object in the military image includes:
Executing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state which stores a first classification result of the military image after evolution;
decoding the output quantum state to obtain a first classification result of the military image;
Inputting the first classification result into the classical convolutional neural network for calculation to obtain a second classification result of the military image;
And determining the military weapon equipment category of the target object in the military image based on the second classification result.
Optionally, before the quantum state evolution corresponding to the quantum convolution neural network is performed on the target quantum state to obtain an output quantum state after evolution and storing the first classification result of the military image, the method further includes:
Acquiring a first number of CNOT gates and a second number of parametric sub-logic gates, and cascading the first number of CNOT gates and the second number of parametric sub-logic gates to obtain a parametric sub-convolution single-layer network;
adding a third quantity of the parameter-containing sub-convolution single-layer networks to the quantum bits to obtain a parameter-containing sub-convolution neural network;
training the parameter-containing sub-convolution neural network through training data to obtain a mapping relation between the training data and parameters of the parameter-containing sub-convolution neural network;
and determining the quantum convolution neural network based on the mapping relation.
Optionally, the training the convolutional neural network containing parameters through training data to obtain a mapping relationship between the training data and the parameters of the convolutional neural network containing parameters includes:
Determining an initial value of a parameter of the parameter-containing sub-logic gate, and calculating the training data through the parameter-containing sub-convolution neural network after the initial value is determined to obtain a predicted value of the training data;
determining a loss value of the training data based on a loss function and a true value corresponding to the predicted value;
When the product of the gradient of the loss value and the learning rate is smaller than or equal to a preset value, taking the initial value as a target value of the parameter-containing sub-logic gate, and establishing a mapping relation between the training data and the parameter of the parameter-containing sub-convolution neural network based on the target value;
and when the product of the gradient of the loss value and the learning rate is larger than a preset value, updating the initial value, and executing the step of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data.
Optionally, the calculating the training data by the parametric sub-convolution neural network after determining the initial value to obtain the predicted value of the training data includes:
And respectively shifting the initial value forwards and backwards by a preset phase to serve as a parameter value of the parameter-containing sub-logic gate, and calculating the training data through a parameter-containing sub-convolution neural network after determining the parameter value to obtain a first sub-predicted value and a second sub-predicted value of the training data.
Optionally, the determining the loss value of the training data based on the loss function, the predicted value and the true value corresponding to the predicted value includes:
Determining a first sub-loss value based on a loss function and the first sub-predicted value and a true value corresponding to the first sub-predicted value, and determining a second sub-loss value based on a loss function and the second sub-predicted value and a true value corresponding to the second sub-predicted value.
Optionally, the gradient of the loss value is specifically determined as follows:
taking 1/2 of the difference between the first sub-loss value and the second sub-loss value as the gradient of the first sub-loss value and the second sub-loss value.
Optionally, the parametric sub-logic gate includes at least one of: the quantum logic gate with parameters U 3, the single quantum logic gate with parameters RX, the single quantum logic gate with parameters RZ and the single quantum logic gate with parameters RZ.
Yet another embodiment of the present application provides a military weapon equipment category determination device, the device comprising:
the acquisition unit acquires military images to be identified;
The coding unit is used for carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
and the determining unit is used for performing evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm to obtain the military weapon equipment category of the target object in the military image.
Optionally, in the aspect of quantum encoding the military image by a quantum image encoding algorithm to obtain a target quantum state, the encoding unit is specifically configured to:
obtaining a quantum bit, a single quantum logic gate RY containing a parameter and a single quantum logic gate RZ containing the parameter;
determining parameter values of the single quantum logic gate RY with the parameters and the single quantum logic gate RZ with the parameters based on pixel values of the military image, and sequentially adding the single quantum logic gate RY and the single quantum logic gate RZ after the parameter values are determined to the quantum bit to obtain a quantum image coding circuit;
And evolving an initial quantum state of the quantum bit to a target quantum state through the quantum image coding circuit.
Optionally, in the determining parameter values of the parameter-containing single-quantum logic gate RY and parameter-containing single-quantum logic gate RZ based on pixel values of the military image, the encoding unit is specifically configured to:
Taking the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum logic gate RY, and taking the square of the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum rotary logic gate RZ.
Optionally, the quantum and classical mixed convolution algorithm includes a quantum convolution neural network and a classical convolution neural network, and in the aspect that the evolution and calculation are performed on the target quantum state by the quantum and classical mixed convolution algorithm to obtain a military weapon equipment category of the target object in the military image, the determining unit is specifically configured to:
Executing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state which stores a first classification result of the military image after evolution;
decoding the output quantum state to obtain a first classification result of the military image;
Inputting the first classification result into the classical convolutional neural network for calculation to obtain a second classification result of the military image;
And determining the military weapon equipment category of the target object in the military image based on the second classification result.
Optionally, before the quantum state evolution corresponding to the quantum convolutional neural network is performed on the target quantum state to obtain an output quantum state after evolution, where the output quantum state of the first classification result of the military image is stored, the determining unit is further configured to:
Acquiring a first number of CNOT gates and a second number of parametric sub-logic gates, and cascading the first number of CNOT gates and the second number of parametric sub-logic gates to obtain a parametric sub-convolution single-layer network;
adding a third quantity of the parameter-containing sub-convolution single-layer networks to the quantum bits to obtain a parameter-containing sub-convolution neural network;
training the parameter-containing sub-convolution neural network through training data to obtain a mapping relation between the training data and parameters of the parameter-containing sub-convolution neural network;
and determining the quantum convolution neural network based on the mapping relation.
Optionally, in the aspect that the training data is used to train the convolutional neural network containing parameters, so as to obtain a mapping relationship between the training data and the parameters of the convolutional neural network containing parameters, the determining unit is specifically configured to:
Determining an initial value of a parameter of the parameter-containing sub-logic gate, and calculating the training data through the parameter-containing sub-convolution neural network after the initial value is determined to obtain a predicted value of the training data;
determining a loss value of the training data based on a loss function and a true value corresponding to the predicted value;
When the product of the gradient of the loss value and the learning rate is smaller than or equal to a preset value, taking the initial value as a target value of the parameter-containing sub-logic gate, and establishing a mapping relation between the training data and the parameter of the parameter-containing sub-convolution neural network based on the target value;
and when the product of the gradient of the loss value and the learning rate is larger than a preset value, updating the initial value, and executing the step of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data.
Optionally, in the aspect that the training data is calculated by the parametric sub-convolution neural network after determining the initial value, to obtain a predicted value of the training data, the determining unit is specifically configured to:
And respectively shifting the initial value forwards and backwards by a preset phase to serve as a parameter value of the parameter-containing sub-logic gate, and calculating the training data through a parameter-containing sub-convolution neural network after determining the parameter value to obtain a first sub-predicted value and a second sub-predicted value of the training data.
Optionally, in the aspect of determining the loss value of the training data based on the loss function, the predicted value and the real value corresponding to the predicted value, the determining unit is specifically configured to:
Determining a first sub-loss value based on a loss function and the first sub-predicted value and a true value corresponding to the first sub-predicted value, and determining a second sub-loss value based on a loss function and the second sub-predicted value and a true value corresponding to the second sub-predicted value.
Optionally, the determining unit is further specifically configured to:
taking 1/2 of the difference between the first sub-loss value and the second sub-loss value as the gradient of the first sub-loss value and the second sub-loss value.
Optionally, the parametric sub-logic gate includes at least one of: the quantum logic gate U 3 with the parameter, the single quantum logic gate RX with the parameter, the single quantum logic gate RY with the parameter and the single quantum logic gate RZ with the parameter.
A further embodiment of the application provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of the preceding claims when run.
Yet another embodiment of the application provides an electronic device comprising a memory having a computer program stored therein and a processor configured to run the computer program to perform the method described in any of the above.
Compared with the prior art, the method for determining the type of the military weapons provided by the invention has the advantages that the acquired military images to be identified are subjected to quantum encoding through the quantum image encoding algorithm, classical data are converted into quantum input, then evolution and calculation are carried out on target quantum states obtained through encoding through the quantum and classical mixed convolution algorithm, and the type of the military weapons of target objects in the military images is obtained, so that the rapid determination of the type of the military weapons of the target objects in the military images is realized, and the speed of military image identification is improved due to the characteristic that the quantum calculation can be carried out in a high-speed parallel manner, so that the determination of the type of the military weapons is realized rapidly, and information support can be provided for military command decisions.
Drawings
FIG. 1 is a hardware block diagram of a computer terminal for a method for determining a class of military weapon equipment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for determining the class of military weapon equipment according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a quantum image encoding circuit according to an embodiment of the present invention;
FIG. 4 is a quantum circuit diagram corresponding to a convolutional single-layer network containing parameters according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a military weapon equipment category determining device according to an embodiment of the present invention.
Detailed Description
The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
The embodiment of the invention firstly provides a military weapon equipment category determining method which can be applied to electronic equipment such as computer terminals, in particular to common computers, quantum computers and the like.
The following describes the operation of the computer terminal in detail by taking it as an example. Fig. 1 is a hardware block diagram of a computer terminal of a military weapon equipment category determining method according to an embodiment of the present invention. As shown in fig. 1, the computer terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing a quantum wire-based military weapon equipment category determination method, and optionally the computer terminal may further include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the computer terminal described above. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the military weapon equipment category determination method in the embodiment of the present application, and the processor 102 executes the software programs and modules stored in the memory 104, thereby performing various functional applications and data processing, i.e. implementing the method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the computer terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.
It should be noted that a real quantum computer is a hybrid structure, which includes two major parts: part of the computers are classical computers and are responsible for performing classical computation and control; the other part is quantum equipment, which is responsible for running quantum programs so as to realize quantum computation. The quantum program is a series of instruction sequences written in a quantum language such as QRunes language and capable of running on a quantum computer, so that the support of quantum logic gate operation is realized, and finally, quantum computing is realized. Specifically, the quantum program is a series of instruction sequences for operating the quantum logic gate according to a certain time sequence.
In practical applications, quantum computing simulations are often required to verify quantum algorithms, quantum applications, etc., due to the development of quantum device hardware. Quantum computing simulation is a process of realizing simulated operation of a quantum program corresponding to a specific problem by means of a virtual architecture (namely a quantum virtual machine) built by resources of a common computer. In general, it is necessary to construct a quantum program corresponding to a specific problem. The quantum program, namely the program for representing the quantum bit and the evolution thereof written in the classical language, wherein the quantum bit, the quantum logic gate and the like related to quantum computation are all represented by corresponding classical codes.
Quantum circuits, which are one embodiment of quantum programs and weigh sub-logic circuits as well, are the most commonly used general quantum computing models, representing circuits that operate on qubits under an abstract concept, and their composition includes qubits, circuits (timelines), and various quantum logic gates, and finally the result often needs to be read out through quantum measurement operations.
Unlike conventional circuits, which are connected by metal lines to carry voltage or current signals, in a quantum circuit, the circuit can be seen as being connected by time, i.e., the state of the qubit naturally evolves over time, as indicated by the hamiltonian operator, during which it is operated until a logic gate is encountered.
One quantum program is corresponding to one total quantum circuit, and the quantum program refers to the total quantum circuit, wherein the total number of quantum bits in the total quantum circuit is the same as the total number of quantum bits of the quantum program. It can be understood that: one quantum program may consist of a quantum circuit, a measurement operation for the quantum bits in the quantum circuit, a register to hold the measurement results, and a control flow node (jump instruction), and one quantum circuit may contain several tens of hundreds or even thousands of quantum logic gate operations. The execution process of the quantum program is a process of executing all quantum logic gates according to a certain time sequence. Note that the timing is the time sequence in which a single quantum logic gate is executed.
It should be noted that in classical computation, the most basic unit is a bit, and the most basic control mode is a logic gate, and the purpose of the control circuit can be achieved by a combination of logic gates. Similarly, the way in which the qubits are handled is a quantum logic gate. Quantum logic gates are used, which are the basis for forming quantum circuits, and include single-bit quantum logic gates, such as Hadamard gates (H gates, ada Ma Men), bery-X gates (X gates), bery-Y gates (Y gates), bery-Z gates (Z gates), RX gates, RY gates, RZ gates, and the like; multi-bit quantum logic gates such as CNOT gates, CR gates, iSWAP gates, toffoli gates, and the like. Quantum logic gates are typically represented using unitary matrices, which are not only in matrix form, but also an operation and transformation. The general function of a quantum logic gate on a quantum state is to calculate through a unitary matrix multiplied by a matrix corresponding to the right vector of the quantum state.
Referring to fig. 2, fig. 2 is a schematic flow chart of a military weapon equipment category determining method according to an embodiment of the present invention. The embodiment provides a military weapon equipment category determining method, which comprises the following steps:
Step 201: acquiring a military image to be identified;
The military image to be identified can be obtained from a front-end interactive interface, and after the military image is obtained, the military image is subjected to size transformation and normalization processing to obtain an input image meeting a quantum image coding algorithm, and the input image is input into the quantum image coding algorithm.
The military image to be identified may be a color image or a gray image, the number of pixels of which is determined based on the number of image channels and the image size, for example, the military image is a 28×28 gray image with 1 channel, and the number of pixels of the military image is 1×28×28=784 pixels; the military image is a 3-channel 32×32 color image, and its pixel count is 3×32×32=3072 pixels. The subsequent quantum image coding algorithm can directly code the color image or convert the color image into a gray image for coding so as to save the quantum bit resource.
Step 202: carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
specifically, in the aspect of quantum encoding the military image through a quantum image encoding algorithm to obtain a target quantum state, the method includes:
obtaining a quantum bit, a single quantum logic gate RY containing a parameter and a single quantum logic gate RZ containing the parameter;
determining parameter values of the single quantum logic gate RY with the parameters and the single quantum logic gate RZ with the parameters based on pixel values of the military image, and sequentially adding the single quantum logic gate RY and the single quantum logic gate RZ after the parameter values are determined to the quantum bit to obtain a quantum image coding circuit;
And evolving an initial quantum state of the quantum bit to a target quantum state through the quantum image coding circuit.
The number of the qubits, the single quantum logic gates RY with the parameters, and the single quantum logic gates RZ with the parameters can be determined based on the pixel point of the military image, one qubit can be used for encoding data of one pixel point, one qubit can be used for encoding data of a plurality of pixel points, the amplitude of the qubit can be used for encoding data of the pixel point, and the quantum state of the qubit can be used for encoding data of the pixel point, so that the method is not limited.
The initial quantum state of the qubit may be |0>, |1>, or an overlapped state of |0> and |1>, which is not limited herein.
For example, if one qubit is used to encode data of one pixel, then a total of 784 pixels are required for a 1-channel 28×28 military image, a total of 784 qubits are required to encode all pixels, and a total of 10×3×32=30720 pixels are required for a total of 10×3×32=30720 pixels for a total of 30720 qubits to encode all pixels. If the available quantum bits of the current quantum computer are limited, all pixels of the military image cannot be coded at one time, the limited quantum bits can be used for carrying out data coding processing on input data in batches, and the circuit is repeatedly constructed for a plurality of times to finish the coding of the whole data.
Specifically, the determining parameter values of the single quantum logic gate RY with parameters and the single quantum logic gate RZ with parameters based on the pixel values of the military image includes:
Taking the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum logic gate RY, and taking the square of the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum rotary logic gate RZ.
For example, if a military image only includes four pixels, the pixel values of which are pix 0、pix1、pix2、pix3, four RY gates and RZ gates are needed to encode the pixels, the parameter values of the four RY gates are as follows ：θ00＝(pix0×π/2)、θ10＝(pix1×π/2)、θ20＝(pix2×π/2)、θ30＝(pix3×π/2);, the parameter values of the four RZ gates are as follows ：θ01＝(pix0×π/2)2、θ11＝(pix1×π/2)2、θ21＝(pix2×π/2)2、θ31＝(pix3×π/2)2. as shown in fig. 3, fig. 3 is a schematic diagram of a quantum image encoding circuit provided in the embodiment of the present invention, wherein the initial quantum state of the quantum bit is |0 >, and the output state is the target quantum state.
Step 203: and performing evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm to obtain the military weapon equipment category of the target object in the military image.
Optionally, the quantum and classical mixed convolution algorithm includes a quantum convolution neural network and a classical convolution neural network, and in the aspect that the evolution and calculation are performed on the target quantum state by the quantum and classical mixed convolution algorithm to obtain a military weapon equipment category of the target object in the military image, the method includes:
Executing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state which stores a first classification result of the military image after evolution;
decoding the output quantum state to obtain a first classification result of the military image;
Inputting the first classification result into the classical convolutional neural network for calculation to obtain a second classification result of the military image;
And determining the military weapon equipment category of the target object in the military image based on the second classification result.
The output quantum state is decoded to obtain a first classification result of the military image, and a reverse circuit of the quantum image coding circuit, namely a logic gate of the quantum image coding circuit is adopted to perform transposition conjugation operation to convert the quantum state into classical data.
The classical convolutional neural network is a classical neural network with ResNet as a main body structure, belongs to the prior art, and is not described herein.
For example, the first classification result is obtained through a quantum convolution neural network, and the first classification result is a tank and corresponding probability thereof, an airplane and corresponding probability thereof, and a ship and corresponding probability thereof; the result of the second classification is the probability of each specific type of tank and corresponding probability of each specific type of aircraft and corresponding probability of each specific type of naval vessel through a classical convolutional neural network.
The determining of the military weapon equipment category of the target object in the military image based on the second classification result may be determining that the military weapon equipment category of the target object in the military image is an airplane of a specific model based on each specific type of airplane and the corresponding probability thereof, or determining that the military weapon equipment category of the target object in the military image is a tank of a specific model based on each specific type of tank and the corresponding probability thereof, or determining that the military weapon equipment category of the target object in the military image is a ship of a specific model based on each specific type of ship and the corresponding probability thereof.
It should be noted that, the type of military weapon equipment of the target object in the military image can be determined by using only the quantum convolution neural network or the classical neural network; whether to determine the military image through two classification processes or one or more processes is not limited herein.
Specifically, before the quantum state evolution corresponding to the quantum convolution neural network is performed on the target quantum state to obtain the output quantum state after the evolution and storing the first classification result of the military image, the method further includes:
Acquiring a first number of CNOT gates and a second number of parametric sub-logic gates, and cascading the first number of CNOT gates and the second number of parametric sub-logic gates to obtain a parametric sub-convolution single-layer network;
adding a third quantity of the parameter-containing sub-convolution single-layer networks to the quantum bits to obtain a parameter-containing sub-convolution neural network;
training the parameter-containing sub-convolution neural network through training data to obtain a mapping relation between the training data and parameters of the parameter-containing sub-convolution neural network;
and determining the quantum convolution neural network based on the mapping relation.
The first number may be the same as or different from the second number, and is not limited herein. The third number is determined according to the complexity of the specific problem to be solved, for example, a two-class problem is relatively simple, two to three quantum convolution layers can be used for solving the problem, the depth of a network is required to be deepened for the complex multi-class problem, a multi-layer quantum convolution network is constructed for solving the problem, and the depth of the network is determined according to the specific requirement.
Wherein the parametric sub-logic gate U (θ) includes at least one of: the quantum logic gate U 3 with the parameter, the single quantum logic gate RX with the parameter, the single quantum logic gate RY with the parameter and the single quantum logic gate RZ with the parameter.
For example, as shown in fig. 4, fig. 4 is a quantum circuit diagram corresponding to a convolutional single-layer network containing parameters according to an embodiment of the present invention. The quantum circuit comprises 4 quantum bit numbers, 4 CNOT gates and 4 parametric sub-logic gates U (theta), wherein the CNOT gates and the U (theta) gates enable the 4 quantum bits to generate entanglement.
Specifically, in the aspect of training the parameter-containing sub-convolutional neural network through training data to obtain a mapping relationship between the training data and parameters of the parameter-containing sub-convolutional neural network, the method includes:
Determining an initial value of a parameter of the parameter-containing sub-logic gate, and calculating the training data through the parameter-containing sub-convolution neural network after the initial value is determined to obtain a predicted value of the training data;
determining a loss value of the training data based on a loss function and a true value corresponding to the predicted value;
When the product of the gradient of the loss value and the learning rate is smaller than or equal to a preset value, taking the initial value as a target value of the parameter-containing sub-logic gate, and establishing a mapping relation between the training data and the parameter of the parameter-containing sub-convolution neural network based on the target value;
and when the product of the gradient of the loss value and the learning rate is larger than a preset value, updating the initial value, and executing the step of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data.
The initial value can be any preset value, and the target value for solving the problem is finally determined through continuous iterative updating of the initial value.
Specifically, in the aspect of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data, the method comprises the following steps:
And respectively shifting the initial value forwards and backwards by a preset phase to serve as a parameter value of the parameter-containing sub-logic gate, and calculating the training data through a parameter-containing sub-convolution neural network after determining the parameter value to obtain a first sub-predicted value and a second sub-predicted value of the training data.
The predetermined phase may be, for example, pi/4, pi/2, 3 pi/4, pi, or other values, which are not limited herein.
Specifically, in determining the loss value of the training data based on the loss function, the predicted value, and the true value corresponding to the predicted value, the method includes:
Determining a first sub-loss value based on a loss function and the first sub-predicted value and a true value corresponding to the first sub-predicted value, and determining a second sub-loss value based on a loss function and the second sub-predicted value and a true value corresponding to the second sub-predicted value.
Wherein, cross entropy loss function is used for classification problem, its concrete form is as follows:
Wherein L (p, q) is a loss value, n is the number of categories, p (x i) is a true tag probability distribution of the classification data, i.e., a true value, and q (x i) is a predicted tag probability distribution of the classification data, i.e., a predicted value.
The mean square error loss function is used for the regression problem, in the following specific form:
Where E is the loss value, k is the data dimension, y k is the predicted value, and t k is the true value.
Wherein the gradient of the loss value is usedOr/>The learning rate is denoted by η. The preset value is a threshold value set empirically in advance.
Specifically, the gradient of the loss value is specifically determined as follows:
taking 1/2 of the difference between the first sub-loss value and the second sub-loss value as the gradient of the first sub-loss value and the second sub-loss value.
The gradient of the loss value is specifically determined as follows:
where α 0 is the initial value of the parameter of the parametric sub-logic gate.
The method for determining the type of the military weapon equipment can simultaneously carry out quantum convolution operation on batch military images, and the quantum circuit has the characteristic of faster calculation than classical bits during calculation operation; meanwhile, the quantum circuit is real-time parallel calculation, a result can be obtained by measuring related bits, and a classical computer needs to perform a large number of multiplication and addition operations to complete the process, so that the time complexity O (log N) of the quantum calculation is smaller than the time complexity O (N 2) of the classical calculation.
Compared with the prior art, the method for determining the type of the military weapons provided by the invention has the advantages that the acquired military images to be identified are subjected to quantum encoding through the quantum image encoding algorithm, classical data are converted into quantum input, then evolution and calculation are carried out on target quantum states obtained through encoding through the quantum and classical mixed convolution algorithm, and the type of the military weapons of target objects in the military images is obtained, so that the rapid determination of the type of the military weapons of the target objects in the military images is realized, and the speed of military image identification is improved due to the characteristic that the quantum calculation can be carried out in a high-speed parallel manner, so that the determination of the type of the military weapons is realized rapidly, and information support can be provided for military command decisions.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a military weapon equipment category determining device according to an embodiment of the present invention, corresponding to the flow described in fig. 2, the device includes:
An acquisition unit 501 that acquires a military image to be identified;
The encoding unit 502 is configured to perform quantum encoding on the military image through a quantum image encoding algorithm, so as to obtain a target quantum state;
The determining unit 503 is configured to perform evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm, so as to obtain a military weapon equipment category of the target object in the military image.
Optionally, in the aspect that the military image is quantum coded by a quantum image coding algorithm to obtain a target quantum state, the coding unit 502 is specifically configured to:
obtaining a quantum bit, a single quantum logic gate RY containing a parameter and a single quantum logic gate RZ containing the parameter;
determining parameter values of the single quantum logic gate RY with the parameters and the single quantum logic gate RZ with the parameters based on pixel values of the military image, and sequentially adding the single quantum logic gate RY and the single quantum logic gate RZ after the parameter values are determined to the quantum bit to obtain a quantum image coding circuit;
And evolving an initial quantum state of the quantum bit to a target quantum state through the quantum image coding circuit.
Optionally, in determining parameter values of the parameter-containing single-quantum logic gate RY and parameter-containing single-quantum logic gate RZ based on pixel values of the military image, the encoding unit 502 is specifically configured to:
Taking the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum logic gate RY, and taking the square of the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum rotary logic gate RZ.
Optionally, the quantum and classical mixed convolution algorithm includes a quantum convolution neural network and a classical convolution neural network, and in the aspect that the evolution and calculation are performed on the target quantum state by the quantum and classical mixed convolution algorithm to obtain a military weapon equipment category of the target object in the military image, the determining unit 503 is specifically configured to:
Executing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state which stores a first classification result of the military image after evolution;
decoding the output quantum state to obtain a first classification result of the military image;
Inputting the first classification result into the classical convolutional neural network for calculation to obtain a second classification result of the military image;
And determining the military weapon equipment category of the target object in the military image based on the second classification result.
Optionally, before the quantum state evolution corresponding to the quantum convolutional neural network is performed on the target quantum state to obtain an output quantum state after the evolution, where the first classification result of the military image is stored, the determining unit 503 is further configured to:
Acquiring a first number of CNOT gates and a second number of parametric sub-logic gates, and cascading the first number of CNOT gates and the second number of parametric sub-logic gates to obtain a parametric sub-convolution single-layer network;
adding a third quantity of the parameter-containing sub-convolution single-layer networks to the quantum bits to obtain a parameter-containing sub-convolution neural network;
training the parameter-containing sub-convolution neural network through training data to obtain a mapping relation between the training data and parameters of the parameter-containing sub-convolution neural network;
and determining the quantum convolution neural network based on the mapping relation.
Optionally, in the aspect that the training data is used to train the convolutional neural network containing parameters, so as to obtain a mapping relationship between the training data and the parameters of the convolutional neural network containing parameters, the determining unit 503 is specifically configured to:
Determining an initial value of a parameter of the parameter-containing sub-logic gate, and calculating the training data through the parameter-containing sub-convolution neural network after the initial value is determined to obtain a predicted value of the training data;
determining a loss value of the training data based on a loss function and a true value corresponding to the predicted value;
When the product of the gradient of the loss value and the learning rate is smaller than or equal to a preset value, taking the initial value as a target value of the parameter-containing sub-logic gate, and establishing a mapping relation between the training data and the parameter of the parameter-containing sub-convolution neural network based on the target value;
and when the product of the gradient of the loss value and the learning rate is larger than a preset value, updating the initial value, and executing the step of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data.
Optionally, in the aspect that the parameter-containing sub-convolution neural network after determining the initial value calculates the training data to obtain a predicted value of the training data, the determining unit 503 is specifically configured to:
And respectively shifting the initial value forwards and backwards by a preset phase to serve as a parameter value of the parameter-containing sub-logic gate, and calculating the training data through a parameter-containing sub-convolution neural network after determining the parameter value to obtain a first sub-predicted value and a second sub-predicted value of the training data.
Optionally, in determining the loss value of the training data based on the loss function, the predicted value, and the real value corresponding to the predicted value, the determining unit 503 is specifically configured to:
Determining a first sub-loss value based on a loss function and the first sub-predicted value and a true value corresponding to the first sub-predicted value, and determining a second sub-loss value based on a loss function and the second sub-predicted value and a true value corresponding to the second sub-predicted value.
Optionally, the determining unit 503 is further specifically configured to:
taking 1/2 of the difference between the first sub-loss value and the second sub-loss value as the gradient of the first sub-loss value and the second sub-loss value.
Optionally, the parametric sub-logic gate includes at least one of: the quantum logic gate U 3 with the parameter, the single quantum logic gate RX with the parameter, the single quantum logic gate RY with the parameter and the single quantum logic gate RZ with the parameter.
A further embodiment of the invention provides a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of the method embodiment of any of the above-mentioned methods when run.
Specifically, in the present embodiment, the above-described storage medium may be configured to store a computer program for executing the steps of:
Acquiring a military image to be identified;
carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
And performing evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm to obtain the military weapon equipment category of the target object in the military image.
Specifically, in the present embodiment, the storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
Still another embodiment of the present invention provides an electronic device comprising a memory having a computer program stored therein and a processor configured to run the computer program to perform the steps of the method embodiment of any of the above.
Specifically, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Specifically, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
Acquiring a military image to be identified;
carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
And performing evolution and calculation on the target quantum state through a quantum and classical mixed convolution algorithm to obtain the military weapon equipment category of the target object in the military image.
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (11)
1. A method of determining a class of military weaponry, the method comprising:
Acquiring a military image to be identified;
carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
Performing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state of a first classification result of the storage military image after evolution; the quantum convolution neural network is determined based on a mapping relation between training data and parameters of a parameter-containing sub-convolution neural network, the mapping relation is obtained by training the parameter-containing sub-convolution neural network through the training data, the parameter-containing sub-convolution neural network is obtained by adding a third number of parameter-containing sub-convolution single-layer networks to quantum bits, and the parameter-containing sub-convolution single-layer networks are obtained by cascading a first number of CNOT gates and a second number of parameter-containing sub-logic gates;
Decoding the output quantum state to obtain image features corresponding to the first classification result of the military image;
Inputting the image features corresponding to the first classification result into a classical convolutional neural network for calculation to obtain a second classification result of the military image;
And determining the military weapon equipment category of the target object in the military image based on the second classification result.
2. The method of claim 1, wherein said quantum encoding the military image by a quantum image encoding algorithm to obtain a target quantum state, comprising:
obtaining a quantum bit, a single quantum logic gate RY containing a parameter and a single quantum logic gate RZ containing the parameter;
determining parameter values of the single quantum logic gate RY with the parameters and the single quantum logic gate RZ with the parameters based on pixel values of the military image, and sequentially adding the single quantum logic gate RY and the single quantum logic gate RZ after the parameter values are determined to the quantum bit to obtain a quantum image coding circuit;
And evolving an initial quantum state of the quantum bit to a target quantum state through the quantum image coding circuit.
3. The method of claim 2, wherein the determining parameter values for the single quantum logic gate with parameters RY and single quantum logic gate with parameters RZ based on pixel values of the military image comprises:
Taking the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum logic gate RY, and taking the square of the product of the pixel value of the military image and pi/2 as the parameter value of the parameter-containing single quantum rotary logic gate RZ.
4. The method of claim 1, wherein training the parametric sub-convolutional neural network with training data to obtain a mapping relationship between the training data and parameters of the parametric sub-convolutional neural network comprises:
Determining an initial value of a parameter of the parameter-containing sub-logic gate, and calculating the training data through the parameter-containing sub-convolution neural network after the initial value is determined to obtain a predicted value of the training data;
determining a loss value of the training data based on a loss function and a true value corresponding to the predicted value;
When the product of the gradient of the loss value and the learning rate is smaller than or equal to a preset value, taking the initial value as a target value of the parameter-containing sub-logic gate, and establishing a mapping relation between the training data and the parameter of the parameter-containing sub-convolution neural network based on the target value;
and when the product of the gradient of the loss value and the learning rate is larger than a preset value, updating the initial value, and executing the step of calculating the training data through the parameter-containing sub-convolution neural network after determining the initial value to obtain the predicted value of the training data.
5. The method of claim 4, wherein the calculating the training data by the parametric sub-convolution neural network after determining the initial value to obtain the predicted value of the training data comprises:
And respectively shifting the initial value forwards and backwards by a preset phase to serve as a parameter value of the parameter-containing sub-logic gate, and calculating the training data through a parameter-containing sub-convolution neural network after determining the parameter value to obtain a first sub-predicted value and a second sub-predicted value of the training data.
6. The method of claim 5, wherein the determining the loss value of the training data based on a loss function and the predicted value and a true value for the predicted value comprises:
Determining a first sub-loss value based on a loss function and the first sub-predicted value and a true value corresponding to the first sub-predicted value, and determining a second sub-loss value based on a loss function and the second sub-predicted value and a true value corresponding to the second sub-predicted value.
7. The method of claim 6, wherein the gradient of loss values is specifically determined as follows:
taking 1/2 of the difference between the first sub-loss value and the second sub-loss value as the gradient of the first sub-loss value and the second sub-loss value.
8. The method of any of claims 1-7, wherein the parametric sub-logic gate comprises at least one of: quantum logic gate containing parametersA single quantum logic gate RX with a parameter, a single quantum logic gate RY with a parameter, a single quantum logic gate RZ with a parameter.
9. A military weapon equipment category determining device, the device comprising:
the acquisition unit is used for acquiring military images to be identified;
The coding unit is used for carrying out quantum coding on the military image through a quantum image coding algorithm to obtain a target quantum state;
The determining unit is used for executing quantum state evolution corresponding to the quantum convolution neural network on the target quantum state to obtain an output quantum state which stores a first classification result of the military image after evolution; the quantum convolution neural network is determined based on a mapping relation between training data and parameters of a parameter-containing sub-convolution neural network, the mapping relation is obtained by training the parameter-containing sub-convolution neural network through the training data, the parameter-containing sub-convolution neural network is obtained by adding a third number of parameter-containing sub-convolution single-layer networks to quantum bits, and the parameter-containing sub-convolution single-layer networks are obtained by cascading a first number of CNOT gates and a second number of parameter-containing sub-logic gates; decoding the output quantum state to obtain image features corresponding to the first classification result of the military image; inputting the image features corresponding to the first classification result into a classical convolutional neural network for calculation to obtain a second classification result of the military image; and determining the military weapon equipment category of the target object in the military image based on the second classification result.
10. A storage medium having a computer program stored therein, wherein the computer program is arranged to perform the method of any of claims 1 to 8 when run.
11. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of any of the claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111319818.6A CN116109854B (en) | 2021-11-09 | 2021-11-09 | Military weapon equipment category determining method and device, medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111319818.6A CN116109854B (en) | 2021-11-09 | 2021-11-09 | Military weapon equipment category determining method and device, medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116109854A CN116109854A (en) | 2023-05-12 |
| CN116109854B true CN116109854B (en) | 2024-06-14 |
Family
ID=86254777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111319818.6A Active CN116109854B (en) | 2021-11-09 | 2021-11-09 | Military weapon equipment category determining method and device, medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116109854B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110738100A (en) * | 2019-09-04 | 2020-01-31 | 沈阳工业大学 | camouflage military target identification method and system based on deep learning |
| CN110909796B (en) * | 2019-11-22 | 2022-05-17 | 浪潮电子信息产业股份有限公司 | Image classification method and related device |
| US20210342730A1 (en) * | 2020-05-01 | 2021-11-04 | equal1.labs Inc. | System and method of quantum enhanced accelerated neural network training |
| CN111751763B (en) * | 2020-06-08 | 2021-08-10 | 武汉大学 | Power transformer winding fault diagnosis method based on GSMallat-NIN-CNN network |
| CN112464003B (en) * | 2020-11-06 | 2023-04-28 | 苏州浪潮智能科技有限公司 | Image classification method and related device |
| AU2021102880A4 (en) * | 2021-05-27 | 2021-10-07 | Meka, James Stephen PROF | A novel system for covid-19 prediction in chest radiography images using hybrid quantum mask r-cnn model |
| CN113361664B (en) * | 2021-08-10 | 2021-11-05 | 北京航空航天大学 | Image recognition system and method based on quantum convolution neural network |
-
2021
- 2021-11-09 CN CN202111319818.6A patent/CN116109854B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Hybrid quantum-classical convolutional neural networks;Junhua Liu et al;《Arxiv》;20191108;全文 * |
| 量子算法及其在图像处理中的应用;庞朝阳;周日贵;丁从宝;胡本琼;;四川师范大学学报(自然科学版);20090720(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116109854A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112633508B (en) | Quantum circuit generation method and device, storage medium and electronic device | |
| CN112232513B (en) | Quantum state preparation method and device | |
| CN114792378B (en) | Quantum image recognition method and device | |
| CN112633507B (en) | Method and device for encoding complex vector to quantum circuit | |
| CN114821217B (en) | Image recognition method and device based on quantum classical hybrid neural network | |
| CN113222155B (en) | Quantum circuit construction method and device, electronic device and storage medium | |
| CN113222153B (en) | Quantum state simulation method and device, storage medium and electronic device | |
| CN113222161B (en) | Implementation method and device of custom quantum logic gate | |
| CN114358319B (en) | Machine learning framework-based classification method and related device | |
| CN114819163B (en) | Training method and device for quantum generation countermeasure network, medium and electronic device | |
| CN114358318B (en) | Machine learning framework-based classification method and related device | |
| CN114358295B (en) | Machine learning framework-based classification method and related device | |
| CN114358216B (en) | Quantum clustering method based on machine learning framework and related device | |
| CN116011682B (en) | Meteorological data prediction method and device, storage medium and electronic device | |
| CN116109854B (en) | Military weapon equipment category determining method and device, medium and electronic device | |
| CN115346080B (en) | Quantum computation-based image processing method and related equipment | |
| CN115809707B (en) | Quantum comparison operation method, device, electronic device and basic arithmetic component | |
| CN114764619A (en) | Convolution operation method and device based on quantum circuit | |
| CN115271076A (en) | Construction method and device of quantum circuit corresponding to Bayesian network | |
| CN116740343B (en) | Image segmentation method and device based on quantum classical mixed neural network | |
| CN114372584B (en) | Transfer learning method based on machine learning framework and related device | |
| CN114764618B (en) | Quantum preprocessing method and device for linear system | |
| CN114821147B (en) | Quantum image recognition display method and device | |
| CN114692879B (en) | Quantum preprocessing method and device based on sparse linear system | |
| CN114819171B (en) | Quantum convolution operation realization method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 230088 6th floor, E2 building, phase II, innovation industrial park, 2800 innovation Avenue, Hefei high tech Zone, Hefei City, Anhui Province Applicant after: Benyuan Quantum Computing Technology (Hefei) Co.,Ltd. Address before: 230088 6th floor, E2 building, phase II, innovation industrial park, 2800 innovation Avenue, Hefei high tech Zone, Hefei City, Anhui Province Applicant before: ORIGIN QUANTUM COMPUTING COMPANY, LIMITED, HEFEI |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |