Super parameter tuning method, apparatus and device

A technology of hyperparameters and parameters, which is applied in the field of hyperparameter tuning methods, devices and equipment, can solve problems such as the complexity of the manual tuning process, and achieve the effect of reducing complexity

Inactive Publication Date: 2019-01-29
沈文策
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The manual tuning process is generally more complicated

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
  • Super parameter tuning method, apparatus and device
  • Super parameter tuning method, apparatus and device
  • Super parameter tuning method, apparatus and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0048] The embodiment of the present invention provides a hyperparameter tuning method, such as figure 1 shown, including:

[0049] S101. Determine hyperparameters to be determined.

[0050] The hyperparameter tuning method provided by the embodiment of the present invention can be applied to electronic devices. Specifically, the electronic device may be a smart phone, a tablet computer, a notebook computer or a desktop computer, and the like.

[0051] Spec...

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 embodiment of the invention provides a super parameter tuning method, an apparatus and a device. The method comprises the following steps: determining a super parameter to be determined; acquiringa preserved super-parameter candidate value combination, wherein the super-parameter candidate value combination comprises a plurality of candidate values of the super-parameter to be determined; traversing each candidate value of the super-parameter to be determined in the super-parameter candidate value combination, and assigning the candidate value to the function parameter in the establishedmodel function, wherein the function parameter is the super-parameter to be determined; running a training model including the model establishing function, and obtaining the model after training; determining the model score corresponding to the model after training; selecting the maximum value of all model scores, wherein, all model scores include the model scores corresponding to each candidate value; the maximum value is determine to be that value of the super-parameter to be determine. The super parameter tuning method, the apparatus and the device provided by the embodiment of the invention can realize the automatic tuning of the super parameter and reduce the complexity of the super parameter tuning process.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a hyperparameter tuning method, device and equipment. Background technique [0002] Hyperparameters are used to define higher-level concepts about the model, such as complexity or learning ability. It can also be understood that hyperparameters are the frame parameters in the machine learning model, such as the number of classes in the clustering method, or the number of topics in the topic model, etc. [0003] In the machine learning process, hyperparameters are parameters that are set before starting the learning process. Cannot be learned directly from data during standard model training, it needs to be pre-defined. [0004] In the current technology, hyperparameter tuning is usually achieved through manual setting. The manual tuning process is generally more complicated. Contents of the invention [0005] The purpose of the embodiments of the present in...

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
IPC IPC(8): G06N3/08
CPCG06N3/08
Inventor 沈文策
Owner 沈文策
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