A learning algorithm of convolution neural network based on limit learning machine

A convolutional neural network and extreme learning machine technology, applied in the field of convolutional neural network learning algorithms, can solve the problems of large memory consumption and slow test time, and achieve the goals of improving training speed, reducing memory consumption, and good generalization performance Effect

Pending Publication Date: 2018-12-25
工极(北京)智能科技有限公司
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a kind of convolutional neural network learning algorithm (abbreviation ELM-CNN) based on extreme learning machine, learn the convolution filter based on extreme learning machine with faster frame, be

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
  • A learning algorithm of convolution neural network based on limit learning machine
  • A learning algorithm of convolution neural network based on limit learning machine
  • A learning algorithm of convolution neural network based on limit learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in further detail below in conjunction with specific embodiments and accompanying drawings.

[0045] A convolutional neural network learning algorithm based on an extreme learning machine. This algorithm is based on the idea of ​​self-encoding to learn a convolution filter with a bias. It includes the following steps:

[0046] Step 1. Convolutional neural network learning algorithm ELM-CNN based on extreme learning machine

[0047] Input: input feature X

[0048] Output: CONV parameters: filter F and bias B

[0049] Normalize the input features to data X with mean 0 and standard deviation 1 N

[0050] Form the desired target T=[X N │1]

[0051] Randomly generate input weight W and bias b

[0052] Calculate hidden matrix H=G(XW+b)

[0053] Calculate the output weight

[0054] Computing Filters and Biases

[0055] Reshape filter matrix F=reshape(F mat )

[0056] Returns the conv parameters filter F and bias B

[0057...

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 convolution neural network learning algorithm based on a limit learning machine, the algorithm is based on the idea of self-encoding to learn the convolutional filter with bias. Firstly, the data matrix is used to generate the standardized training data with the mean value of 0 and variance of 1. Secondly, the data matrix is used to generate the standardized training datawith the mean value of 0 and variance of 1. Then the convolution deviation is processed, the intercept term is added, and the normalized input and intercept terms are reconstructed so that the objective matrix becomes a formula shown in the specification. Given input and objective matrix, and reshaping matrix are used to obtain a filter. The invention is based on an automatic coding limit learning machine, which learns a convolution filter, and is used for training arbitrary convolution neural network to work, dealing with the deviation of the filter, and reconstructing a standardized input with an intercept term. The invention is a hierarchical training process, does not need the entire classification model to extract arbitrary features, improves the training speed, realizes a competitive result in the generalization performance, and exceeds the BP in the training speed. CNN; while memory consumption is reduced.

Description

technical field [0001] The present invention relates to the technical field of computer artificial intelligence, specifically a convolutional neural network learning algorithm based on an extreme learning machine. This algorithm is based on the idea of ​​self-encoding to learn a convolution filter with deviations. Through reconstruction, it has Normalized input for the intercept term to close the gap between extreme learning machines and deep learning. Background technique [0002] Thanks to deep learning breakthroughs in the ImageNet Large-Scale Visual Recognition Challenge, all winning architectures have a convolutional structure. Moreover, many convolutional neural networks (referred to as CNN) have been successfully applied in different fields, such as object recognition, speech recognition, natural language processing and other fields. The convolutional neural network is trained with the BP algorithm by backpropagating the classification error, and the gradient descent...

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
CPCG06N3/08G06N3/084
Inventor 马宏宾费庆李楠楠克莱
Owner 工极(北京)智能科技有限公司
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