Supercharge Your Innovation With Domain-Expert AI Agents!

Over-limit learning machine modeling method based on conjugate gradient method

A technology of extreme learning machine and conjugate gradient method, applied in the field of extreme learning machine theory, can solve the problems of high cost, slow response speed and high bit error rate

Inactive Publication Date: 2016-07-27
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the gradient descent method also exposes problems such as high cost, high bit error rate, and slow response speed.

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
  • Over-limit learning machine modeling method based on conjugate gradient method
  • Over-limit learning machine modeling method based on conjugate gradient method
  • Over-limit learning machine modeling method based on conjugate gradient method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] Embodiment: the modeling method of the present invention is to carry out the following steps on the computer and realize:

[0029] Step 1: Model Selection

[0030] Given a training sample set N={(x i ,t i )|i=1,…,N}, where each input vector x i =[x 1i ,x 2i ,...,x ni ] consists of n-dimensional data, each ideal output vector t i =[t 1i ,t 2i ,...,t mi ] consists of m-dimensional data, and the number of nodes in the given network hidden layer is set to The weight W from the input layer to the hidden layer is one matrix, bias b is a A vector, where the value of each element is 1, and the hidden layer activation function is denoted as G(w i ,b i ,x), the hidden layer activation function chooses the sigmoid function or other functions, and the error function is E=||Y-T|| 2 ;

[0031] Step 2. Parameter initialization

[0032] Randomly assign the initial weight matrix W from the input layer to the hidden layer 0 ; Preferably, the random assignment takes a ...

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 an over-limit learning machine modeling method based on a conjugate gradient method, and belongs to the technical field of an over-limit learning machine theory. The modeling method involves executing the such steps on a computer as model selection, parameter initialization, initial weight optimization and test precision obtaining. The training speed is faster than that of a correlation algorithm based on steepest descent method. At the same time, since weights from an input layer to a hidden layer are iterated and optimized by use of the conjugate gradient method after random selection, under the condition that the same training precision is reached, the quantity of hidden-layer nodes needed by the method provided by the invention is far smaller than the quantity of hidden-layer nodes needed for an over-limit learning machine algorithm.

Description

technical field [0001] The invention belongs to the technical field of extreme learning machine theory, and in particular relates to an improved extreme learning machine modeling method based on a conjugate gradient method. Background technique [0002] Advanced neural activities such as human behavior, thoughts and emotions are all dominated and controlled by the brain, so the brain contains a wealth of useful information. How to effectively acquire and use these effective information of the brain has always been a hot issue that researchers have paid attention to. EEG signals are mainly caused by the event-related potential changes in the cerebral cortex caused by the interaction between a large number of interconnected neurons in the brain. It is one of the important means to obtain brain information at present. Brain-computer interface technology establishes a channel that can directly transmit information between the brain and external devices (such as computers or oth...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 王健龚晓玲叶振昀时贤温艳青杨国玲张炳杰
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com