Neural network model optimization method based on class expansion learning

A neural network model and neural network technology, applied in the field of neural network model optimization based on class expansion learning, can solve problems such as high implementation cost, no migration ability, and difficulty in reproduction.

Active Publication Date: 2020-02-14
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this type of optimization method has many details, high implementation cost, and difficult to reproduce; on the other hand, this typ

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
  • Neural network model optimization method based on class expansion learning
  • Neural network model optimization method based on class expansion learning
  • Neural network model optimization method based on class expansion learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0106] The following simulation experiment is carried out based on the above method. The implementation method of this embodiment is as described above, and the specific steps are not described in detail. The following only shows the results of the experiment results.

[0107]This embodiment uses three complex networks, namely ResNet-18, ResNet-30 and ResNet-110. And repeated training experiments were carried out on the three data sets CIFAR10, CIFAR100, and ImageNet-100 of image classification tasks, which proved that this method can effectively improve the optimization effect of neural networks. Among them, the parameters M=10, K=5 in the data set CIFAR10; the parameters M=100, K=10 in the data set CIFAR100; the parameters M=100, K=10 in the data set ImageNet-100. The implementation effects of the method of the present invention and the traditional neural network model optimization method on the three data sets are shown in Table 1.

[0108] Table 1 Implementation effect of...

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 neural network model optimization method based on class expansion learning. The method specifically comprises the following steps: obtaining a data set which is used for training and contains various types of samples, and defining an algorithm target; extracting features of each type of pictures in the data set by using a universal model, and evaluating the error-prone degree of each type according to the distribution condition of each type of features; adding several types of data with the highest error-prone degree into a training pool, and optimizing the neural network by using the data in the training pool; after the optimization is completed, adding the remaining data with the highest error-prone degree into a training pool, expanding the categories in the training pool, and further optimizing the neural network by using the training pool on the basis of the neural network obtained by the last training; and continuously performing class expansion on the training pool until the whole data set enters the training pool to obtain a final optimized neural network model. The method is suitable for neural network model optimization based on multi-class datasets in supervised learning, and has good effect and robustness for various complex conditions.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a neural network model optimization method based on class expansion learning. Background technique [0002] The optimization method of the neural network model is the underlying technology of artificial intelligence, and it is often used as the basis for high-level visual tasks, such as object detection, target recognition, semantic segmentation, etc. However, limited by computer computing resources and memory resources, current optimization methods for neural network models rely on batch stochastic gradient descent. This method is an iterative, batch-level learning model. Each training cannot use global data, but only one batch of data. Since the data for each training is usually distributed in an extremely sparse and scattered space, the optimization of the neural network model is very difficult, and it will be affected by most of the simple data while optimizing, ignoring the i...

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): G06N20/00G06N3/04G06N3/08
CPCG06N20/00G06N3/04G06N3/082
Inventor 汪慧朱文武赵涵斌李玺
Owner ZHEJIANG 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