Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Neural network training method and device, storage medium and electronic device

A neural network training and neural network technology, applied in the fields of neural network training methods and devices, storage media and electronic devices, can solve problems such as long training time, low neural network training efficiency, and no solution proposed, so as to ensure training efficiency , Solve the effect of low training efficiency and expanding the sample range

Active Publication Date: 2019-05-07
TENCENT TECH (SHENZHEN) CO LTD
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] That is to say, the neural network training method provided in the related art requires a long training time, which leads to the problem of low neural network training efficiency
[0005] For the above problems, no effective solution has been proposed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network training method and device, storage medium and electronic device
  • Neural network training method and device, storage medium and electronic device
  • Neural network training method and device, storage medium and electronic device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] In an embodiment of the present invention, an embodiment of the above neural network training method is provided. As an optional implementation, the neural network training method can be applied to, but not limited to, such as figure 1 In the shown application environment, a client of a human-computer interaction application is installed in the terminal 102. For example, a game application is used as an example to describe the human-computer interaction application. Object A is an object controlled by a user, and object B is an object controlled by a machine. Obtain offline samples by running the human-computer interaction application and store them in the database 104, where the database 104 can be located in the training control server, but can also be located in a third-party independent server without limitation; further, the acquisition meets the predetermined A set of offline samples used to train the neural network composed of offline samples of configuration con...

Embodiment 2

[0093] According to an embodiment of the present invention, a neural network training device for implementing the above neural network training method is also provided, such as Figure 8 As shown, the device includes:

[0094] 1) The obtaining unit 802 is configured to obtain an offline sample set for training a neural network in a human-computer interaction application, wherein the offline sample set includes offline samples satisfying predetermined configuration conditions;

[0095] 2) The offline training unit 804 is used to train the initial neural network offline using the offline sample set to obtain the object neural network, wherein, in the human-computer interaction application, the processing capability of the object neural network is higher than that of the initial neural network;

[0096] 3) The online training unit 806 is configured to connect the object neural network to the online operating environment of the human-computer interaction application for online tra...

Embodiment 3

[0155] According to an embodiment of the present invention, an electronic device for implementing the above neural network training method is also provided, such as Figure 10 As shown, the electronic device includes: one or more (only one is shown in the figure) processor 1002 , memory 1004 , display 1006 , user interface 1008 , and transmission device 1010 . Wherein, the memory 1004 can be used to store software programs and modules, such as program instructions / modules corresponding to the security vulnerability detection method and device in the embodiment of the present invention, and the processor 1002 runs the software programs and modules stored in the memory 1004 to execute Various functional applications and data processing, that is, to realize the detection method of the above-mentioned system vulnerability attack. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flas...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a neural network training method and device, a storage medium and an electronic device. The method comprises the steps that an offline sample set used for training a neural network in a human-computer interaction application is acquired, and the offline sample set comprises offline samples meeting preset configuration conditions; The initial neural network is trained offline by using the offline sample set to obtain an object neural network, and in the human-computer interaction application, the processing capability of the object neural network is higher than that of the initial neural network; And the object neural network is accessed to an online operation environment of the human-computer interaction application for online training to obtain a target neural network. According to the invention, the technical problem of low training efficiency in the neural network training method provided by the related technology is solved.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a neural network training method and device, a storage medium and an electronic device. Background technique [0002] Deep Q Network (Deep Q Network, DQN for short) algorithm is a method of integrating convolutional neural network and Q-Learning, which is applied to Deep Reinforcement Learning (DRL for short). Deep learning and reinforcement learning are combined to realize a brand new algorithm for end-to-end learning from perception to action. That is to say, after the sensory information is input, the action is directly output through the deep neural network, so that the robot can realize the potential of fully autonomous learning and even multiple skills, thereby realizing the artificial intelligence (AI) operation. In order to enable the robot to better complete autonomous learning and apply it proficiently in different scenarios, it has become an urgent problem to obtain t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06N3/04
CPCG06N3/04G06N3/08
Inventor 杨夏张力柯
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com