A structure search method and system of convolution neural network based on evolutionary algorithm

A technology of convolutional neural network and network structure, applied in the field of convolutional neural network structure search based on evolutionary algorithm, can solve the problems such as the inability to scale and uncertainty of artificially designed models, and achieve the effect of process flow and good certainty.

Active Publication Date: 2019-02-01
SUN YAT SEN UNIV
View PDF6 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention: In order to solve the shortcomings of manual design models that cannot be scaled, streamlined, and uncertain, it provides a convolutional neural network structure search method and system based on evolutionary a

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 structure search method and system of convolution neural network based on evolutionary algorithm
  • A structure search method and system of convolution neural network based on evolutionary algorithm
  • A structure search method and system of convolution neural network based on evolutionary algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Such as figure 1 As shown, the implementation steps of the evolutionary algorithm-based convolutional neural network structure search method in this embodiment include:

[0046] 1) Input data set and set preset parameters;

[0047] 2) Initialize the population according to the preset parameters to obtain the initial population;

[0048] 3) if figure 2 As shown, through the controller T as the main thread C Pop the initial population into queue Q and start queue manager T Q and message manager T M , the queue manager T Q After opening, untrained chromosomes in the queue Q will be ejected and decoded, and then a worker manager T as an independent temporary thread will be opened. W Calculate the fitness for its training, and the queue manager T Q Terminate after the number of individuals who have completed training reaches the total number of search models in the preset parameters, and according to the worker manager T W The status update dictionary W, the diction...

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 structure searching method and a system based on an evolutionary algorithm. The method comprises the steps of inputting a data set and setting preset parameters to obtain an initial population. By the controller TC as the main thread popping the initial population into the queue q and opening the queue manager tq and the message manager tm, After the queue manager TQ is turned on, the untrained chromosomes in the queue Q are pop-up and decoded, and a worker manager TW as an independent temporary thread is started to calculate the fitness forthe training, Through the cooperation of controller TC, queue manager TQ, worker manager TW and message manager TM, the parallel search of convolution neural network structure based on evolutionary algorithm is completed and the best model is output. The invention can realize automatic modeling, parameter adjustment and training for a given data set, has the advantages of high performance, large-scale, flow-chart and good certainty, and is particularly suitable for deployment and implementation on a high-performance computer cluster.

Description

technical field [0001] The invention relates to the field of model design of deep learning, in particular to a convolutional neural network structure search method and system based on an evolutionary algorithm, which is a solution for automatic modeling, parameter adjustment and training for a given data set. Background technique [0002] Due to the rapid development of computer software and hardware, the computing power and storage space of equipment have been greatly improved, and many large-scale data sets have emerged. These conditions make it very effective to use a deep convolutional neural network to process large-scale image data sets. Among them, excellent models such as AlexNet, VGGNet, ResNet, and GoogleNet have emerged. Each model sets a fixed operator combination structure. The current convolutional neural network mainly includes operators such as convolution, pooling, and full connection. Many operators need to set some precise parameters. For example, a convol...

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): G06F16/2453G06N3/00
CPCG06N3/006
Inventor 卢宇彤瞿毅力郑馥丹陈志广
Owner SUN YAT SEN UNIV
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