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

Convolutional Neural Network Algorithm Based on Echo State Network Classification

A technology of echo state network and convolutional neural network, which is applied in the field of signal processing and can solve problems such as poor performance, large computing resources, and occupation

Active Publication Date: 2022-06-21
SOUTHEAST UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current CNN algorithm generally has the problem of high training time cost, which makes it take up a lot of computing resources; at the same time, CNN does not perform well on small sample data sets, and is prone to overfitting

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
  • Convolutional Neural Network Algorithm Based on Echo State Network Classification
  • Convolutional Neural Network Algorithm Based on Echo State Network Classification
  • Convolutional Neural Network Algorithm Based on Echo State Network Classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] This simulation experiment is carried out on a server with a main frequency of 2.5GHz, 12 cores, CPU model Intel Xeon E5-2678v3, and memory of 64GB, using MATLAB R2016b as the editor of the algorithm.

[0060] Here, the number of convolution kernels of the two convolutional layers C2 and C4 of CNN and E-CNN is set to 6 and 16, and the sizes are both 5×5; the modes of the two down-sampling layers P3 and P5 are both MEAN and the sampling area Both are 2 × 2; the activation function is selected as the sigmoid function, and the learning rate is set to 1. E-CNN's reserve pool size N R =1000, the state activation function of the reserve pool is tanh, the output activation function is the linear output function, and the regularization parameter λ=1×e -7 , the idling of the reserve pool is also no longer set here.

[0061] The parameters of the CNN model pre-trained on the CIFAR-10 dataset are used as the initial values ​​of the experiments. Pads zeros around the 28*28 size ...

Embodiment 2

[0069] This simulation experiment is carried out on a server with a main frequency of 2.5GHz, 12 cores, CPU model Intel Xeon E5-2678v3, and memory of 64GB, using MATLAB R2016b as the editor of the algorithm.

[0070] Here, the number of convolution kernels of the two convolutional layers C2 and C4 of CNN and E-CNN is set to 6 and 16, and the sizes are both 5×5; the modes of the two down-sampling layers P3 and P5 are both MEAN and the sampling area Both are 2 × 2; the activation function is selected as the sigmoid function, and the learning rate is set to 1. E-CNN's reserve pool size N R =1000, the state activation function of the reserve pool is tanh, the output activation function is the linear output function, and the regularization parameter λ=1×e -7 , the idling of the reserve pool is also no longer set here.

[0071] The parameters of the CNN model pre-trained on the CIFAR-10 dataset are used as the initial values ​​of the experiments. Pads zeros around the 28*28 size ...

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 provides a convolutional neural network algorithm based on echo state network classification, mainly comprising: replacing the fully connected layer in the CNN model with ESN, and deriving a new residual iteration formula, on this basis, the model continues to use the CNN method The backpropagation algorithm trains the hidden layer parameters of the CNN, and trains the output weights of the ESN using the linear regression rule. The feasibility of the present invention is proved by the simulation experiments on the MNIST handwritten digit recognition data set, the Fashion MNIST object recognition data set and the ORL face recognition data set. At the same time, the experimental results reflect that the model not only retains the features of CNN multi-level feature extraction ability, and by introducing the ESN module to reduce the training time of the algorithm and improve its performance on small sample data sets.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a convolutional neural network algorithm based on echo state network classification. Background technique [0002] Convolution Neural Network (CNN) is a deep neural network that can automatically extract multi-level features of images. It has the characteristics of weight sharing, sparse connection and pooling operations, making it widely used in object detection, areas such as face recognition and natural language processing. However, the current CNN algorithm generally has the problem of high training time cost, which makes it occupy a lot of computing resources; at the same time, CNN does not perform well on small sample data sets, and is prone to overfitting. How to solve these two problems is the current research focus of CNN optimization algorithm. SUMMARY OF THE INVENTION [0003] In order to solve the above problems, the present invention provides a convolut...

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 Patents(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/084G06N3/045
Inventor 夏亦犁王新裴文江
Owner SOUTHEAST UNIV
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