CN111461328A - Neural network training method and electronic equipment - Google Patents
Neural network training method and electronic equipment Download PDFInfo
- Publication number
- CN111461328A CN111461328A CN202010259862.1A CN202010259862A CN111461328A CN 111461328 A CN111461328 A CN 111461328A CN 202010259862 A CN202010259862 A CN 202010259862A CN 111461328 A CN111461328 A CN 111461328A
- Authority
- CN
- China
- Prior art keywords
- prediction result
- sample data
- prediction
- preset
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012549 training Methods 0.000 title claims abstract description 68
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012545 processing Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000013522 software testing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a training method of a neural network, which comprises the following steps: inputting task information into a preset learning model to obtain sample data, wherein the task information is used for indicating the characteristics of the sample to be obtained; the method for training the neural network can well guide the neural network to conduct autonomous learning, is high in efficiency and good in training accuracy.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a training method of a neural network and electronic equipment.
Background
In the field of artificial intelligence technology, various functions can be realized by using a neural network, for example, a certain signal processing or image recognition is completed by using the neural network, when a target task of a user is processed by using the neural network, the neural network generally needs to be trained first, so that the processing effect of the neural network reaches the requirement standard of the user, a large amount of sample data needs to be manually screened in the training process, the efficiency of the training process is low, the effect is poor, and the accuracy of the neural network is affected.
Disclosure of Invention
In view of the above, one of the technical problems to be solved by the present application is to provide a training method for a neural network and an electronic device, which can guide the neural network to perform autonomous learning.
The embodiment of the application provides a training method of a neural network, which comprises the following steps: inputting task information into a preset learning model to obtain sample data, wherein the task information is used for indicating the characteristics of the sample to be obtained;
the prediction model is processed according to the sample data to obtain a prediction result;
and when the prediction result meets a preset condition, determining that the preset learning model completes training.
Optionally, in an embodiment of the present application, when the prediction result satisfies a predetermined condition, determining that the preset learning model completes training includes:
and when the difference between the prediction result and the last prediction result is smaller than or equal to a preset difference value, determining that the preset learning model completes training.
Optionally, in an embodiment of the present application, the training method of the neural network further includes:
when the prediction result does not meet the preset condition, inputting the difference between the prediction result and the last prediction result and the task information into the preset learning model to obtain new sample data;
and inputting the new sample data into the prediction model to obtain a new prediction result.
Optionally, in an embodiment of the present application, when the prediction result does not satisfy the predetermined condition, inputting a difference between the prediction result and a previous prediction result and the task information into the preset learning model to obtain new sample data, and inputting the new sample data into the prediction model to obtain a new prediction result, further including:
and when the difference between the prediction result and the last prediction result is larger than a preset difference value, determining that the prediction result does not meet the preset condition.
Optionally, in an embodiment of the present application, the obtaining, by the prediction model, a prediction result according to the sample data includes:
constructing a knowledge graph of the sample data;
and inputting the knowledge graph into the prediction model to obtain the prediction result.
The embodiment of the present application further provides a training system for a neural network, including: a learning module and a prediction module, wherein the learning module and the prediction module,
the learning module is used for inputting the task information into a preset learning model to obtain sample data;
the prediction module is used for obtaining a prediction result for the sample data by using a prediction model, and determining that the preset learning model completes training when the prediction result meets a preset condition;
optionally, in an embodiment of the application, the prediction module is further configured to determine that the preset learning model completes training when a difference between the prediction result and the last prediction result is less than or equal to a preset difference value.
Optionally, in an embodiment of the application, when the prediction result does not satisfy the predetermined condition, the prediction module inputs a difference between the prediction result and a last prediction result and the task information into the preset learning model to obtain new sample data;
and inputting the new sample data into the prediction model to obtain a new prediction result.
Optionally, in an embodiment of the application, the prediction module is further configured to determine that the prediction result does not satisfy the predetermined condition when a difference between the prediction result and a last prediction result is greater than a preset difference value.
Optionally, in an embodiment of the present application, the training system of the neural network further includes a knowledge graph construction module, where the knowledge graph construction module is configured to construct a knowledge graph of the sample data;
the prediction module is further configured to input the knowledge graph into the prediction model to obtain the prediction result.
The embodiment of the application provides a training method and a system of a neural network, comprising the following steps: the method for training the neural network can effectively guide the neural network to conduct autonomous learning, and is high in efficiency and good in accuracy.
Drawings
Fig. 1 is a flowchart of a method for training a neural network according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for training a neural network according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;
fig. 4 is a hardware structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application, and the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application shall fall within the scope of the protection of the embodiments in the present application.
The following further describes specific implementations of embodiments of the present application with reference to the drawings of the embodiments of the present application.
The first embodiment,
As shown in fig. 1, fig. 1 is a flowchart of a neural network training method provided in the embodiment of the present application, including:
s101, inputting task information into a preset learning model to obtain sample data, wherein the task information is used for indicating the characteristics of the sample to be obtained;
in the embodiment of the present application, inputting task information into a preset learning model to obtain sample data includes: determining data to be learned according to the description of the trained target task by using a preset learning model, for example, the preset learning model can determine detailed data of the target task through tools such as internet, sensor, simulation software and the like according to header data of data related to the trained target task included in task information, and determine the detailed data as sample data of the trained target task, of course, the sample data may also be sample data determined in a manual screening manner, and this embodiment merely exemplifies a manner of obtaining the number of samples by using the preset learning model, and does not represent that the present application is limited thereto;
in this embodiment, the preset learning model is a deep learning model based on deep learning, and the preset learning model is a neural network that can learn a mapping relationship between various data related to target task information and target task content, for example, header data of a target task is input to the preset learning model, and a batch of sample data and detailed parameters of the sample data related to the target task can be output, so that training speed is effectively increased, and the amount of learned data is reduced.
S102, processing the sample data by using a prediction model to obtain a prediction result;
in an implementation manner of this embodiment, the prediction model is a neural network model based on Graph Neural Networks (GNNs), and the Graph neural network model can perform pattern recognition and data mining better.
Optionally, in an implementation manner of this embodiment, the sample data may be data directly obtained by using a preset learning model, or data information related to the sample data, which is obtained by presetting the relevant information of the trained target task in the learning model, and determining the sample data as a data set obtained by internet, sensor, simulation software and other tools according to the data information;
and inputting the determined sample data into a prediction model to obtain a prediction result.
Optionally, in an implementation manner of the embodiment of the present application, processing the sample data by using a prediction model to obtain a prediction result further includes:
constructing a knowledge graph of sample data;
and inputting the knowledge graph into a prediction model to obtain a prediction result.
Optionally, constructing a knowledge graph of sample data includes: and determining data in the sample data into nodes in the knowledge graph, and constructing the knowledge graph of the sample data according to the knowledge nodes.
The edges of the knowledge graph are relations among data in the sample data, each node of the directed attribute graph of the knowledge graph comprises a plurality of attributes and attribute values, and the knowledge graph adopts character strings which are easy to recognize to identify the sample data, so that the sample data can be easily recognized and processed by a computer, and the prediction efficiency of the prediction model is improved.
S103, when the prediction result meets a preset condition, determining that the preset learning model completes training.
Optionally, in this embodiment of the application, when the prediction result meets the predetermined condition, determining that the preset learning model completes training includes: and when the difference between the prediction result and the last prediction result is smaller than or equal to a preset difference value, determining that the preset learning model completes training.
In an implementation manner of this embodiment, the preset difference may be a numerical value, and the magnitude of the preset difference may be preset or set according to a target task or other manners, and of course, this embodiment of this application only exemplifies an example to describe the preset difference, and does not represent that the application is limited to this;
in the embodiment of the application, the smaller the preset difference is, the better the preset difference is, the smaller the difference between the prediction result and the previous prediction result is, which indicates that the sample data density obtained by the preset learning model is higher, so that the prediction result obtained according to the sample data tends to be consistent, and the training accuracy of the preset learning model is better finally.
Optionally, in this embodiment of the present application, the training method of the neural network further includes: when the prediction result does not meet the preset condition, inputting the difference between the prediction result and the last prediction result and the task information of the training into a preset learning model to obtain new sample data;
and inputting the new sample data into the prediction model to obtain a new prediction result.
When the prediction result does not meet the preset condition, it is indicated that the density of sample data acquired by the preset model is low, and the data is scattered and not comprehensive enough, so that the error between the prediction result obtained by the prediction model according to the current sample data and the actual data is large, the data density of the current sample data needs to be improved by continuously using the appropriate sample data, and the data with the improved data density is used as the sample data again to train the neural network, so that the training result of the neural network after obtaining sufficient and comprehensive sample data has better accuracy.
Optionally, in an implementation manner of the embodiment of the present application, obtaining new sample data by using a preset learning model further includes:
determining new sample data according to the last prediction result and the sample data corresponding to the last prediction result, for example, the preset learning model may determine data to be learned by the current preset learning model according to the last prediction result, so as to add the determined data to be learned to the last sample data as new sample data; in another implementation manner of this embodiment, the preset learning model may update the current sample data according to the prediction result of the current sample data by using tools such as internet, sensor, simulation software, and the like, so as to obtain new sample data. The implementation mode of new sample data is determined according to the previous prediction result and the sample data corresponding to the previous prediction result, so that the preset learning model can acquire the data required to be learned more accurately, the total amount of the sample data required to be acquired by the neural network in the training process is reduced, the training accuracy of the neural network is guaranteed, and meanwhile, the training efficiency of the neural network is improved.
Optionally, in an implementation manner of this embodiment, when the prediction result does not satisfy the predetermined condition, acquiring new sample data by using a preset learning model, and inputting the prediction result and the new sample data into the prediction model to obtain a new prediction result, including;
when the difference between the prediction result and the last prediction result is larger than a preset difference value, acquiring new sample data by using a preset learning model, and inputting the prediction result and the new sample data into the prediction model to obtain a new prediction result;
in the implementation manner of this embodiment, the preset learning model is determined to acquire new sample data by using the preset difference value, so that it is determined that the neural network needs to continue training and learning, the determination process of determining whether the neural network completes training according to the prediction result can be simplified, and the efficiency of neural network training is improved. The preset difference value may be a numerical value, and the numerical value may be manually set or determined in other manners, which is not limited in this application.
The embodiment provides a training method of a neural network, which comprises the following steps: inputting task information into a preset learning model to obtain sample data, wherein the task information is used for indicating the characteristics of the sample to be obtained; the method for training the neural network can well guide the neural network to conduct autonomous learning, is high in efficiency and good in training accuracy.
Example II,
Based on the training method of the neural network described in the first embodiment, the first embodiment exemplifies an actual application scenario, and for example, a training process of the neural network for predicting the antenna performance is described to describe the training method of the neural network described in the first embodiment.
In actual life, when measuring antenna performance, can involve and be surveyed a large amount of test points of antenna, if test each point of antenna one by one, then must lead to the required work load of test procedure very huge, the inefficiency of test, it is with high costs, nevertheless obtain the test data of being surveyed a small number of test points of antenna through utilizing neural network, predict the whole performance of antenna, the work load that can effectual reduction test, improve efficiency of software testing, reduce test cost.
In this embodiment, as shown in fig. 2, fig. 2 is a flowchart of a training method of a neural network provided in an embodiment of the present application, where the method includes the following steps:
s201, inputting simulation test data of the antenna performance into a preset learning model to obtain sample data of the antenna performance.
Optionally, in an implementation manner of the embodiment regarding obtaining sample data of antenna performance, the preset learning model may provide data information such as frequency (f), position (x, y, z) and the like of an antenna to be tested according to simulation data of antenna performance, and a user may obtain a level value E (f, x, y, z) of the frequency and the position by arranging a test tool to a position specified by the position (x, y, z) information according to the position (x, y, z) information provided by the preset learning model and adjusting the test tool to the specified frequency (f) of the antenna provided by the preset learning model, so as to determine the sample data of antenna performance according to the frequency (f), the position (x, y, z) and the corresponding level value E (f, x, y, z).
Processing the sample data of the antenna performance by using a prediction model to obtain a prediction result:
in an implementation manner of this embodiment, processing sample data of antenna performance by using a prediction model to obtain a prediction result further includes:
s202, establishing a knowledge graph of the sample data according to the sample data of the antenna performance.
Optionally, in an implementation manner of this embodiment, a knowledge graph of the sample data is established according to the sample number data of the antenna performance, including;
the frequency (f), position (x, y, z) and level value E (f, x, y, z) in the sample data of the antenna performance are used as attributes of the node in the knowledge graph, that is, the node V is (E, f, x, y, z), and the knowledge graph of the sample data is constructed.
And when the prediction result meets a preset condition, determining that the neural network predicting the antenna performance completes training.
And S203, determining a prediction result of the antenna performance according to the knowledge graph of the current sample data by using the prediction model.
In an implementation manner of this embodiment, when the prediction result of the antenna performance satisfies a predetermined condition, determining that the neural network predicting the antenna performance completes training includes:
and S204, determining a batch of new sample data according to the prediction result determined by the sample data by using a preset learning model.
In an implementation manner of this embodiment, determining a batch of new sample data includes determining a batch of test points of new antenna performance according to a prediction result determined by current antenna performance sample data by using a preset learning model, obtaining a level value E (f, x, y, z) of the batch of new test points through a test tool according to frequency (f) and position (x, y, z) information of the batch of new test points, and using data of frequency (f), position (x, y, z) and level value E (f, x, y, z) in previous sample data as the new sample data of the antenna performance.
And S205, constructing a knowledge graph of new sample data.
S206, obtaining a new prediction result of the antenna performance according to the knowledge graph of the new sample data by using the prediction model; the new prediction result includes the remaining frequency (f), the position (x, y, z) and the corresponding level value E (f, x, y, z).
S207, comparing the difference between the current prediction result and the previous prediction result;
and S208, determining whether the difference meets a preset condition.
S209, if the preset conditions are met, finishing training; and if the preset condition is not met, jumping to S204 until the difference between the prediction result determined by the sample data updated by the preset learning model and the prediction result of the previous sample data meets the preset condition, and determining that the training of the neural network for predicting the antenna performance is completed.
In one implementation manner of this embodiment, when the difference satisfies the predetermined condition, it is determined that the data learned by the neural network for predicting the antenna performance has reached a sufficient data density, the accuracy of the neural network prediction after training is high, and the current training may be ended.
When the difference does not meet the preset condition, the density of the sample data currently learned by the preset learning model is low, a large error exists between the predicted antenna performance and the actual performance, the sample data needs to be continuously updated, training is continuously carried out by utilizing the preset learning model and the prediction model, and the training effect with high precision is achieved.
Optionally, in an implementation manner of this embodiment, the predetermined condition for antenna prediction may be set as a preset difference, where the preset difference may be a number, and the number may be manually set or determined in another manner, and the predetermined condition is set as a numerical value, so that a process of determining a difference between a prediction result of new sample data and a prediction result of previous sample data can be simplified, and thus, the efficiency of neural network training is improved.
Example III,
Based on the training method for the neural network provided in the first embodiment of the present application, a third embodiment of the present application provides an electronic device for training the neural network, as shown in fig. 3, fig. 3 is a schematic structural diagram of the electronic device provided in the first embodiment of the present application, and the method includes: a learning module 301 and a prediction module 302,
the learning module 301 is configured to input task information into a preset learning model to obtain sample data;
the prediction module 302 is configured to obtain a prediction result by using the sample data, and when the prediction result meets a predetermined condition, determine that a preset learning model completes training;
optionally, in an implementation manner of this embodiment, the prediction module 302 is further configured to determine that the preset learning model completes training when a difference between the prediction result and the last prediction result is less than or equal to a preset difference value.
Optionally, in an implementation manner of this embodiment, the predicting module 302 is further configured to, when the prediction result does not meet the predetermined condition, input a difference between the prediction result and the previous prediction result and task information into the preset learning model to obtain new sample data, and input the new sample data into the prediction model to obtain a new prediction result.
Optionally, in an implementation manner of this embodiment, when a difference between the prediction result and the last prediction result is greater than the preset difference, the prediction model 302 determines that the prediction result does not satisfy the predetermined condition.
Optionally, in an embodiment of the present application, the electronic device further includes a knowledge graph constructing module 303, where the knowledge graph constructing module 303 is configured to construct a knowledge graph of the sample data;
the prediction module 302 is further configured to input the knowledge graph of the sample data into the prediction model to obtain a prediction result of the sample data.
Example four,
Based on the description of the foregoing embodiments, this embodiment further provides a storage medium, as shown in fig. 4, fig. 4 is a hardware structure diagram of an electronic device provided in this embodiment, where the hardware of the electronic device further includes:
one or more processors 401;
a storage medium 402, the storage medium 402 configured to store one or more readable programs 412;
when executed by the one or more processors 401, the one or more programs 412 cause the one or more processors to implement a method of training a neural network as in any of the embodiments described above.
The hardware also includes a communication interface 403 and a communication bus 404;
the processor 401, the storage medium 402 and the communication interface 403 complete communication with each other through the communication bus 404;
wherein, the processor 401 may be specifically configured to: and obtaining sample data by using the preset learning model, obtaining a prediction result by the prediction model according to the sample data, and determining the preset learning model to finish training when the prediction result meets a preset condition.
The neural network trained electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) a mobile communication device: such devices are characterized by mobile communications capabilities and are primarily targeted at providing voice, data communications. Such terminals include: smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) Ultra mobile personal computer device: the equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include: PDA, MID, and UMPC devices, etc., such as ipads.
(3) A portable entertainment device: such devices can display and play multimedia content. This type of device comprises: audio, video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.
(4) And other electronic equipment with data interaction function.
Thus, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular transactions or implement particular abstract data types. The application may also be practiced in distributed computing environments where transactions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method of training a neural network, comprising:
inputting task information into a preset learning model to obtain sample data, wherein the task information is used for indicating the characteristics of the sample to be obtained;
processing the sample data by using a prediction model to obtain a prediction result;
and when the prediction result meets a preset condition, determining that the preset learning model completes training.
2. The training method of the neural network according to claim 1, wherein the determining that the preset learning model completes training when the prediction result satisfies a predetermined condition includes:
and when the difference between the prediction result and the last prediction result is less than or equal to the preset difference value, determining that the preset learning model completes training.
3. The method of training a neural network of claim 1, further comprising:
when the prediction result does not meet the preset condition, inputting the difference between the prediction result and the last prediction result and the task information into the preset learning model to obtain new sample data;
and inputting the new sample data into the prediction model to obtain a new prediction result.
4. The method of training a neural network of claim 4, further comprising:
and when the difference between the prediction result and the last prediction result is larger than the preset difference value, determining that the prediction result does not meet the preset condition.
5. The method of claim 1, wherein the predicting model obtains the prediction result according to the sample data, and comprises:
constructing a knowledge graph of the sample data;
and inputting the knowledge graph into the prediction model to obtain the prediction result.
6. An electronic device, comprising: a learning module and a prediction module, wherein the learning module and the prediction module,
the learning module is used for inputting the task information into a preset learning model to obtain sample data;
and the prediction module is used for processing the sample data by using a prediction model to obtain a prediction result, and determining that the preset learning model completes training when the prediction result meets a preset condition.
7. The electronic device of claim 6,
and the prediction module determines that the preset learning model completes training when the difference between the prediction result and the last prediction result is less than or equal to the preset difference value.
8. The electronic device of claim 6,
the prediction module is further configured to, when the prediction result does not satisfy the predetermined condition, input a difference between the prediction result and a last prediction result and the task information into the preset learning model to obtain new sample data;
and inputting the new sample data into the prediction model to obtain a new prediction result.
9. The electronic device of claim 6,
the prediction module is further configured to determine that the prediction result does not satisfy the predetermined condition when a difference between the prediction result and the last prediction result is greater than the preset difference value.
10. The electronic device of claim 6,
the system also comprises a knowledge graph construction module, wherein the knowledge graph construction module is used for constructing a knowledge graph of the sample data;
the prediction module is further configured to input the knowledge graph into the prediction model to obtain the prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010259862.1A CN111461328B (en) | 2020-04-03 | 2020-04-03 | Training method of neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010259862.1A CN111461328B (en) | 2020-04-03 | 2020-04-03 | Training method of neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461328A true CN111461328A (en) | 2020-07-28 |
| CN111461328B CN111461328B (en) | 2024-04-30 |
Family
ID=71681642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010259862.1A Active CN111461328B (en) | 2020-04-03 | 2020-04-03 | Training method of neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461328B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515896A (en) * | 2021-08-06 | 2021-10-19 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108898218A (en) * | 2018-05-24 | 2018-11-27 | 阿里巴巴集团控股有限公司 | A kind of training method of neural network model, device and computer equipment |
| CN109325508A (en) * | 2017-07-31 | 2019-02-12 | 阿里巴巴集团控股有限公司 | The representation of knowledge, machine learning model training, prediction technique, device and electronic equipment |
| CN110163201A (en) * | 2019-03-01 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Image measurement method and apparatus, storage medium and electronic device |
| CN110210654A (en) * | 2019-05-20 | 2019-09-06 | 南京星火技术有限公司 | Product model designing system and method |
-
2020
- 2020-04-03 CN CN202010259862.1A patent/CN111461328B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325508A (en) * | 2017-07-31 | 2019-02-12 | 阿里巴巴集团控股有限公司 | The representation of knowledge, machine learning model training, prediction technique, device and electronic equipment |
| CN108898218A (en) * | 2018-05-24 | 2018-11-27 | 阿里巴巴集团控股有限公司 | A kind of training method of neural network model, device and computer equipment |
| CN110163201A (en) * | 2019-03-01 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Image measurement method and apparatus, storage medium and electronic device |
| CN110210654A (en) * | 2019-05-20 | 2019-09-06 | 南京星火技术有限公司 | Product model designing system and method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113515896A (en) * | 2021-08-06 | 2021-10-19 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
| CN113515896B (en) * | 2021-08-06 | 2022-08-09 | 红云红河烟草(集团)有限责任公司 | Data missing value filling method for real-time cigarette acquisition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461328B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288082B (en) | Convolutional neural network model training method and device and computer readable storage medium | |
| CN109976998B (en) | Software defect prediction method and device and electronic equipment | |
| CN109376419B (en) | Data model generation method and device, electronic equipment and readable medium | |
| CN111611390B (en) | Data processing method and device | |
| CN110069997B (en) | Scene classification method and device and electronic equipment | |
| CN116894188A (en) | Service tag set updating method and device, medium and electronic equipment | |
| CN111461328B (en) | Training method of neural network | |
| CN113392018B (en) | Traffic distribution method and device, storage medium and electronic equipment | |
| CN117236805B (en) | Power equipment control method, device, electronic equipment and computer readable medium | |
| CN116246787B (en) | Risk prediction method and device for non-recurrent death | |
| CN114049530A (en) | Hybrid precision neural network quantization method, device and equipment | |
| CN112766402A (en) | Algorithm selection method and device and electronic equipment | |
| CN116560968A (en) | Simulation calculation time prediction method, system and equipment based on machine learning | |
| CN109977925B (en) | Expression determination method and device and electronic equipment | |
| CN108416426B (en) | Data processing method, device and computer readable storage medium | |
| CN115774854A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113961765B (en) | Searching method, searching device, searching equipment and searching medium based on neural network model | |
| CN109429282B (en) | Frequency point configuration method and device | |
| CN115203556A (en) | Score prediction model training method and device, electronic equipment and storage medium | |
| CN112307371B (en) | Applet sub-service identification method, device, equipment and storage medium | |
| CN108229572A (en) | A kind of parameter optimization method and computing device | |
| CN108055638A (en) | Obtain method, apparatus, computer-readable medium and the equipment of target location | |
| CN113592557A (en) | Attribution method and device of advertisement putting result, storage medium and electronic equipment | |
| CN111582456A (en) | Method, apparatus, device and medium for generating network model information | |
| CN115618962B (en) | Model training method, business wind control 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |