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

Regularization-based RBF network multi-label classification method

A technology of RBF network and classification method, which is applied in the field of regularized RBF network multi-label classification, which can solve the problems of reducing the generalization performance of classification methods, the problem of not being able to classify multiple labels, and the classification results that cannot be obtained by classification methods.

Inactive Publication Date: 2015-11-11
NORTHWEST UNIV(CN) +2
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is aimed at multi-instance multi-label problems, and cannot be directly used to solve a single multi-label classification problem, and this method does not perform regularization processing, so that the classification method cannot obtain optimal classification results
[0005] The above RBF network multi-label classification methods do not use regularization technology, which limits the classification results of the classification method and reduces the generalization performance of the classification method

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
  • Regularization-based RBF network multi-label classification method
  • Regularization-based RBF network multi-label classification method
  • Regularization-based RBF network multi-label classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0112] This example takes the Yeast dataset as an example. The dataset belongs to the field of biology and includes 1500 training samples and 917 test samples. The training samples are used to train a multi-label classification system, and the test samples are used as samples with unknown labels for label prediction. The Yeast dataset has 103-dimensional features and 14 labels, with an average number of labels of 4.24 and a label density of 0.303.

[0113] Regularized RBF network multi-label classification method, such as figure 1 As shown, using a training data set containing 1500 samples to construct an RBF network includes 3 steps, and the specific process is as follows:

[0114] Step 1: The network input layer includes 103 nodes;

[0115] Step 2: Label space with dimension 14 for the dataset for each label in , find the positive sample set in the training data set For clustering, the specific steps are:

[0116] 1) Label collection label y in 1 , find out the po...

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 regularization-based RBF network multi-label classification method and belongs to the field of multi-label classification technique. According to the technical scheme of the invention, the method comprises the steps of (1) constructing an RBF network, namely, constructing the input layer nodes, the hidden layer nodes and the output layer nodes of the network; (2) training the RBF network based on training data; (3) predicting labels based on the RBF network. The multi-label classification method is designed based on the regularization technique and is fast in clustering speed and good in generalization performance. Therefore, the generalization performance of the RBF network can be effectively enhanced.

Description

technical field [0001] The invention belongs to the technical field of multi-label classification, and in particular relates to a regularized RBF network multi-label classification method. Background technique [0002] Under the framework of traditional machine learning, the classification problem studies how to accurately divide the samples to be classified into a unique class. If there are only two candidate classes, this type of problem is called a binary classification problem. If there are more than one candidate class, this type of problem is called a multi-class classification problem. Binary classification problems and multi-class classification problems are both single-label classification problems. However, in the real world, ambiguous objects with multiple conceptual labels at the same time widely exist. For example, in document classification, each document may belong to multiple topics at the same time, and a news report can be divided into "politics" and "ec...

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): G06N3/04
Inventor 孙霞王佳荣冯筠陈勇吴宁海
Owner NORTHWEST UNIV(CN)
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