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

Efficient neural network structure design method based on layer-by-layer progressive mode

A network structure, progressive technology, applied in the field of efficient neural network structure search

Inactive Publication Date: 2021-09-03
HUNAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Future methods may further improve search time, model accuracy, inference delay, etc.

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
  • Efficient neural network structure design method based on layer-by-layer progressive mode
  • Efficient neural network structure design method based on layer-by-layer progressive mode
  • Efficient neural network structure design method based on layer-by-layer progressive mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0065] A kind of efficient neural network search method based on layer-by-layer progressive includes the following steps:

[0066] Step 1. Assuming that training and testing are performed on Cifar-10, the search space combined with SEMBconv and Bottleneck is used, the layer-by-layer search strategy is used, and the evaluation method for weighted scoring of accuracy and delay time is used.

[0067] Step 2. The algorithm uses SEMBconv and Bottleneck to search the space. The search space has 28 operations. Assuming that the operation space has n layers, then the search space has 28 n a network model.

[0068] Step 3. The algorithm uses a layer-by-layer search strategy to divide the network into undetermined layers and definite layers ( figure 1 ), the specific method can be divided into single-layer training and fusion training, and t...

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 an efficient neural network structure design method based on a layer-by-layer progressive mode. The objective of the invention is to solve the problem of huge time overhead of neural network structure search, so that efficient neural network structure search is realized by adopting a layer-by-layer progressive method, the network structure of the layer is searched from a single-layer neural network structure, all currently found layers are fused and trained, then the network structure of the next layer is searched, and the specified layer number is reached. According to the method, an excellent neural network model which enables the search time to be within an acceptable range of common computing power, and is high in model accuracy and short in reasoning time delay can be found.

Description

technical field [0001] The invention relates to a method for designing a deep neural network structure in the field of artificial intelligence, in particular to an efficient neural network structure search method. Background technique [0002] In recent years, deep learning technology has achieved great success in a large number of computational vision tasks, and deep neural structure is a key factor in determining performance. Research on fully automatic neural structure search methods has received more and more attention in recent years. [0003] An excellent network model must have a unique model structure, and the design of these model structures requires sufficient experience. In the industry, the commonly used model structure is the residual network (Res-18, Res-34), which is applied in almost all fields of machine learning, such as image classification, target detection, semantic segmentation, etc., and can even combine two The three-dimensional convolutional neural ...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 刘星宇熊伟明王涛蒋佳王易梁虹金鑫徐航
Owner HUNAN 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