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

Improved evolutionary neural network architecture search method based on super network

A neural network and search method technology, applied in the field of image classification model construction, can solve problems such as slow convergence speed and inability to converge

Pending Publication Date: 2021-03-26
上海悠络客电子科技股份有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the insufficiency of the hypernetwork-based neural network architecture search method in the prior art, and the supernetwork training convergence speed is slow or even unable to converge, the technical problem to be solved by the present invention is to provide a supernetwork-based evolutionary neural network architecture A search method that uses evolutionary algorithms as a search strategy to automatically generate neural network architectures based on hypernetworks to improve classification accuracy for image classification tasks

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
  • Improved evolutionary neural network architecture search method based on super network
  • Improved evolutionary neural network architecture search method based on super network
  • Improved evolutionary neural network architecture search method based on super network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0068] like Figure 1 to Figure 3 As shown, the present embodiment provides an improved hypernetwork-based evolutionary neural network architecture search method, which mainly includes the following contents:

[0069] In the first step, the input layer is used as the first layer, and five computing modules are encapsulated; M computing nodes are encapsulated in each module, and finally the fully connected layer is used as the output layer of the neural network; in this embodiment, each computing module is set Contains 9 computing nodes, that is, M=9; the input layer is sequentially composed of convolutional layer, ReLU activation function and batch normalization (Batch Normalization, BN) layer encapsulation; the computing node is a computing unit in the neural network , which can be randomly selected from the operating search space θ...

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 an improved evolutionary neural network architecture search method based on a super network. The method comprises the following steps of S1, taking an input layer as a first layer, and packaging five calculation modules; S2, binarizing the connection of the computing nodes in the neural network; S3, learning a structure weight for each computing node, and S4, constructinga parent population P by adopting a binary fancy competition selection method. S5, forming a filial generation population Q; and S6, performing mutation operation on individuals in the filial generation population Q. S7, decoding each individual in the filial generation population Q into a corresponding neural network to obtain a structural weight; and S8, combining the parent population P and thechild population Q into a population R, selecting a plurality of individuals as an original population of the next generation by adopting an environment selection method, and feeding back to the stepS4 until a predetermined maximum evolution algebra is reached, and after the evolution is finished, outputting the individual with the highest fitness value as the optimal neural network architecture.

Description

technical field [0001] The invention relates to the technical field of image classification model construction, in particular to an improved supernetwork-based evolutionary neural network architecture search method. Background technique [0002] The image classification task is an image processing technology that distinguishes different types of targets based on the different feature information reflected in the picture. Since many models applied to image classification tasks can be transferred to other computer vision fields as feature extraction networks, image classification tasks are a basic task in the field of computer vision, and the design of image classification models is also a hot spot for researchers. However, manual design of neural network models requires experienced experts to design neural network models with excellent performance through careful research on the distribution and characteristics of data sets and trial and error. Therefore, huge time and labor...

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 Applications(China)
IPC IPC(8): G06N3/04G06N3/063G06N3/00G06K9/62
CPCG06N3/006G06N3/063G06N3/045G06F18/214
Inventor 金耀初沈修平
Owner 上海悠络客电子科技股份有限公司
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