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

Method and device for building neural network

A neural network and equipment technology, which is applied in the field of neural networks and can solve problems affecting the prediction accuracy of the final neural network.

Inactive Publication Date: 2016-11-23
NEC CORP
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when there are enough training samples, this method of randomly discarding hidden layer nodes will affect the prediction accuracy of the final neural network.

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
  • Method and device for building neural network
  • Method and device for building neural network
  • Method and device for building neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Hereinafter, various exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. It should be noted that these drawings and description relate to preferred embodiments as examples only. It should be noted that, from the ensuing description, alternative embodiments of the structures and methods disclosed herein are readily conceivable and may be employed without departing from the disclosed principles of the present disclosure as claimed.

[0030] It should be understood that these exemplary embodiments are given only to enable those skilled in the art to better understand and implement the present disclosure, but not to limit the scope of the present disclosure in any way. In addition, in the drawings, for the purpose of illustration, optional steps, modules, units, etc. are shown in dotted line boxes.

[0031] The terms "including", "comprising" and similar terms used herein should be understood as open-ende...

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 a method and a device for building a neural network. The method comprises the following steps: acquiring an correlation relation model between target data and influence factors thereof, wherein the correlation relation model characterizes the correlation between the target data and the influence factors thereof; setting the network topology of a neural network according to the correlation relation model; and training the neural network using sample data. According to the invention, an improved method for building a neural network is provided, and the network topology of a neural network is set according to a correlation relation model between input and output data. By using the method, the time for network training can be saved greatly, without influencing the model prediction accuracy.

Description

technical field [0001] The present disclosure relates to neural network technology, and more particularly to a method and device for constructing a neural network. Background technique [0002] A neural network is a complex network system formed by extensively interconnecting a large number of simple processing units called "neurons". Neural network can reflect many basic features of human brain function, it is a highly complex nonlinear dynamic learning system. Typically, a neural network model is represented by network topology, node characteristics, and learning rules. The network topology of a neural network includes the number of layers of the network, the number of neurons in each layer, and the way each neuron is connected to each other. Neural networks have proven to be a very effective approach and are widely used in areas such as prediction, image and speech pattern recognition, and function optimization. But at the same time, neural networks also have disadvant...

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 张霓胡卫松
Owner NEC CORP
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