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

Multilayer decomposition fuzzy neural network optimization design method

A fuzzy neural network and multi-layer decomposition technology, which is applied in the field of multi-layer decomposition fuzzy neural network optimization design, can solve problems such as the limited function fitting ability of the decomposition fuzzy neural network

Pending Publication Date: 2020-02-07
HENAN UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the function fitting ability of the existing decomposed fuzzy neural network is limited, the present invention proposes a multi-layer decomposed fuzzy neural network optimization design 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
  • Multilayer decomposition fuzzy neural network optimization design method
  • Multilayer decomposition fuzzy neural network optimization design method
  • Multilayer decomposition fuzzy neural network optimization design method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further explained below in conjunction with accompanying drawing and specific embodiment:

[0049] The structural framework of multi-layer decomposition fuzzy neural network is as follows: figure 1 shown in figure 1 In , the input layer only transmits data, so the output of the input layer X=(x 1 ,...,x n ). The role of the first hidden layer is to extract features from the output of the input layer, namely Y 1 O =F 1 (X), where l 1 =1,...,m 1 . The input of the second hidden layer is the output of the input layer and the output of the first hidden layer, namely Dimension is n+m 1 , which outputs Y 2 O =F 2 (Y 2 I ), where F 2 , Y 2 O similar to F 1 , Y 1 O ,Y 2 O The dimension is m 2 . By analogy, the input and output vectors of the third to Lth hidden layers can be obtained where L represents the number of hidden layers. The input of the output layer is the output of the input layer and the output of all h...

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 the field of computer science artificial intelligence, and discloses a multilayer decomposition fuzzy neural network design method. The whole design process comprises structural design and parameter optimization of the model. In the aspect of model structure design, a kernel-based fuzzy clustering algorithm is adopted to determine the number of component fuzzy neural networks in a hidden layer, and the number of layers for decomposing the fuzzy neural networks is determined according to the maximum threshold value of the number of the hidden layer networks and model precision; in the aspect of parameter optimization, a least square method is adopted to optimize connection weights among an input layer, a hidden layer and an output layer. An intermolecular scalar coupling constant prediction problem is adopted as a specific embodiment, and the effectiveness of the model provided by the invention is verified.

Description

technical field [0001] The invention belongs to the technical field of computer science and artificial intelligence, and in particular relates to a multi-layer decomposition fuzzy neural network optimization design method. Background technique [0002] In order to effectively describe the ubiquitous uncertain phenomena in nature, Zadeh proposed a fuzzy system paradigm based on fuzzy sets. On this basis, the fuzzy system has achieved success in the field of system modeling and control, but the design of the fuzzy system lacks adaptability and self-organization, and it is difficult to adapt to the time-varying characteristics of complex systems. The effect is not good in practical applications. The neural network has a powerful self-learning ability, combining it with the fuzzy system into a fuzzy neural network makes it both interpretable and learnable. However, the approximation performance of traditional fuzzy neural networks is still limited. In order to further improve ...

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): G06N3/04G06N3/08G06K9/62G06F17/16
CPCG06N3/08G06F17/16G06N3/043G06N3/045G06F18/23213
Inventor 赵亮谢志峰张坤鹏金军委付园坤
Owner HENAN UNIVERSITY OF TECHNOLOGY
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