Hyper-parameter optimization device and method

An optimization method and technology for optimizing devices, applied in the field of artificial intelligence, can solve problems such as a large amount of data and poor parallelism, and achieve the effect of improving optimization efficiency and reducing human input.

Inactive Publication Date: 2020-05-15
SHANGHAI YITU NETWORK SCI & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Chinese invention patent application CN110110862A discloses a hyperparameter optimization method based on an adaptive model, which is

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 optimization device and method
  • Hyper-parameter optimization device and method
  • Hyper-parameter optimization device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. 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.

[0074] It should be noted that in this article, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these No such actual relationship or order exists between entities or operations.

[0075] The inventors of this solution fo...

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 hyper-parameter optimization method, and the method comprises the following steps: 1, extracting all hyper-parameters included in an algorithm model and vectorizing all the hyper-parameters to form hyper-parameter vectors; 2, assigning values to the hyper-parameter vectors and changing the values of the hyper-parameter vectors; 3, evaluating the performance of the algorithm model corresponding to the hyper-parameter vectors with various values, forming corresponding evaluation values, and selecting the value of the hyper-parameter vector with the best evaluation valueas the final optimization value of the hyper-parameter vector. The invention further discloses a hyper-parameter optimization device. According to the method, the algorithm hyper-parameters can be automatically optimized, so a better model can be obtained after the algorithm model is trained while the human input is reduced.

Description

technical field [0001] The present invention relates to artificial intelligence (Artificial Intelligence, AI), in particular to a hyperparameter optimization device. The invention also relates to a hyperparameter optimization method. Background technique [0002] Model parameters and model hyperparameters in machine learning differ in their roles, sources, and more. In simple terms, a model parameter is a configuration variable inside the model whose value can be estimated from data. Specifically, model parameters have the following characteristics: model parameters are required for model prediction; model parameter values ​​can define model functions; model parameters are obtained by data estimation or data learning; model parameters are generally not manually set by practitioners; A portion of a model is kept; model parameters are typically estimated using an optimization algorithm, which is an efficient search for possible values ​​for the parameters. Some examples of ...

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): G06K9/62G06N20/00G06N3/08G06N3/00
CPCG06N20/00G06N3/086G06N3/006G06F18/23213G06F18/24G06F18/214
Inventor 章子誉王益县
Owner SHANGHAI YITU NETWORK SCI & TECH
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