Hyper-parameter tuning method and device and model construction method and device

A technology of hyperparameters and models, which is applied in the field of data processing and can solve problems such as the inability to construct neural network models.

Active Publication Date: 2020-03-17
TENCENT TECH (SHENZHEN) CO LTD
View PDF26 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on this, it is necessary to provide a hyperparameter tuning method and device, a Model construction method and device, a computer-readable storage medium and computer equipment

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
  • Hyper-parameter tuning method and device and model construction method and device
  • Hyper-parameter tuning method and device and model construction method and device
  • Hyper-parameter tuning method and device and model construction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0055] figure 1 It is an application environment diagram of the hyperparameter tuning method in an embodiment. refer to figure 1 , the hyperparameter tuning method is applied to the model training system. The model training system includes at least a training server 110 and an evaluation server 120 . The training server 110 and the evaluation server 120 are connected through a network. The training server 110 and the evaluation server 120 can be implemented by independent servers or server clusters composed of multiple servers.

[0056] Wherein, the training server 11...

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 relates to a hyper-parameter tuning method and device and a model construction method and device. The hyper-parameter tuning method comprises the steps of obtaining a first neural network model obtained after an initial neural network model is trained; training the first neural network model to obtain a second neural network model; obtaining the model growth degree of the second neural network model relative to the first neural network model according to the difference between the second model capability evaluation value and the first model capability evaluation value; screeningout a growth potential model from the second neural network model according to the model growth degree; and obtaining an optimal hyper-parameter according to the hyper-parameter in the growth potential model. According to the invention, elimination of hyper-parameters with growth potential can be avoided.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a hyperparameter tuning method and device, a model building method and device, a computer-readable storage medium and computer equipment. Background technique [0002] At present, neural network models are mainly constructed manually. For example, artificially design hyperparameters and common parameters, use hyperparameters and common parameters to construct a neural network model for controlling game characters to operate in the game environment, apply the neural network model in the game, and make the game character It can simulate the operation of real players and realize the game characters with artificial intelligence (AI, Artificial Intelligence). [0003] Common parameters in the neural network model, such as weight values, bias values, etc., can be tuned through iterative training. Hyperparameters such as the number of convolutional layers and the num...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/214Y02T10/40
Inventor 欧阳显斌周飞虎王洋子豪魏杰乾赵秀峰
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap