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

Predication method and device based on echo state network (ESN)

A technology of echo state network and prediction method, which is applied in the field of communication and can solve problems such as no formation

Inactive Publication Date: 2015-09-16
杨凤琴
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although there is a lot of research on how to obtain a "good" dynamic pool related to specific problems, there is no systematic method, and most of the research is only carried out from the perspective of experiments, which is also the largest problem encountered by ESN methods. challenge

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
  • Predication method and device based on echo state network (ESN)
  • Predication method and device based on echo state network (ESN)
  • Predication method and device based on echo state network (ESN)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] An embodiment of the present invention provides a prediction method based on an echo state network, the echo state network ESN is composed of an input layer, an intermediate layer and an output layer, the input layer is composed of X input units, and the intermediate layer is composed of Y intermediate units, the Y intermediate units form a first dynamic pool, and the output layer is composed of Z output units, wherein a connection matrix W is provided between the input layer and the intermediate layer in , a first internal matrix W is provided between the Y intermediate units of the intermediate layer, and a feedback matrix W is provided between the output layer and the intermediate layer back , there is a connection matrix W between the output layer and the ESN out , X, Y, Z are integers greater than 0, such as figure 2 shown, including:

[0061] 101. The prediction device establishes a second dynamic pool, and the second dynamic pool is composed of N small-world d...

Embodiment 2

[0092] Embodiments of the present invention provide a prediction method based on echo state network, such as Figure 4 shown, including:

[0093] 201. The prediction device establishes a standard ESN echo state network prediction model.

[0094] Specifically, the predicting device may establish a typical three-layer ESN echo state network, which is an input layer, an output layer, and an intermediate layer. The input layer is composed of input units, as the input of the ESN network, if there are K input units, the input dimension of the ESN network is K; the output layer is composed of output units, and outputs the predicted results, if the output layer output units are L , that is, the output dimension of the ESN network is L. The intermediate layer is composed of intermediate units. If there are N intermediate units, the input layer and the intermediate layer units are connected to each other to form a K*N connection matrix W in , all three layers of ESN and the output la...

Embodiment 3

[0150] Embodiments of the present invention provide a prediction device based on echo state network, such as Figure 6 As shown, the echo state network ESN is composed of an input layer, an intermediate layer and an output layer, the input layer is composed of X input units, the intermediate layer is composed of Y intermediate units, and the Y intermediate units constitute the first A dynamic pool, the output layer is composed of Z output units, wherein a connection matrix W is set between the input layer and the middle layer in , a first internal matrix W is provided between the Y intermediate units of the intermediate layer, and a feedback matrix W is provided between the output layer and the intermediate layer back , there is a connection matrix W between the output layer and the ESN out , X, Y, and Z are integers greater than 0, and the device includes:

[0151] The acquisition module 01 is used to establish a second dynamic pool, the second dynamic pool is composed of N...

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 embodiment of the invention provides a predication method and a device based on an echo state network (ESN), which relates to the communication field. Through generating a plurality of small-world and non-scale dynamic pool groups, the type and the topology structure of an original ESN dynamic pool structure are changed, and better predication effects can be generated for a nonlinear chaotic time system. The method comprises steps: a second dynamic pool is built, wherein the second dynamic pool is composed of N small-world dynamic pools and Y non-scale dynamic pools according to a complex network theory, and N and Y are larger than 0; a first dynamic pool replaces the second dynamic pool, and a lateral boundary suppression mechanism is used for associating the N small-world dynamic pools in the second dynamic pool with the N non-scale dynamic pools; a training set with a specified length is inputted to update the second dynamic pool, and a connection matrix Wout after updating is further obtained; and according to the Wout after updating, the following formula is used for predication: y(n+1)=f<out>(Wout(u(n+1), x(n+1), y(n))).

Description

technical field [0001] The invention relates to the communication field, in particular to a prediction method and device based on an echo state network. Background technique [0002] Artificial Neural Networks (ANNs for short), also referred to as neural networks (NNs) or connection models (Connection Model), is a kind of algorithmic mathematics that imitates the behavior characteristics of animal neural networks and performs distributed parallel information processing. Model. This kind of network relies on the complexity of the system to achieve the purpose of processing information by adjusting the interconnection of a large number of internal nodes. It is characterized by distributed storage of information and parallel collaborative processing. On the basis of network model and algorithm research, there are many practical application systems composed of artificial neural networks, for example, to complete certain signal processing or pattern recognition functions, to con...

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): G06N3/02
Inventor 杨凤琴
Owner 杨凤琴
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