Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Deep migration learning system and method based on entropy minimization

A technology of transfer learning and minimum entropy, which is applied in the field of learning systems to achieve fast convergence and high classification accuracy

Inactive Publication Date: 2019-12-17
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a deep transfer learning method based on entropy minimization to solve the ordinary solution problem that occurs when only entropy minimization technology is used

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
  • Deep migration learning system and method based on entropy minimization
  • Deep migration learning system and method based on entropy minimization
  • Deep migration learning system and method based on entropy minimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0035] figure 1 is a flow chart of a deep transfer learning method based on entropy minimization provided by an embodiment of the present invention, as shown in figure 1 As shown, the method includes:

[0036] Step S1, according to different transfer learning tasks, divide the source domain and the target domain, construct a transfer learning network, and initialize network hyperparameters.

[0037] Constructing the transfer learning network based on the feature extractor and the classifier;

[0038] It can be understood that the migration learning network provided by the embodiment of the present invention is composed of two parts: a feature extractor and a label classifier, the feature extractor is used to extract the features of the input sample set, and the classifier is used to perform predictive classification.

[0039] Specifically, taki...

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 provides a deep migration learning method based on entropy minimization, and the method comprises the steps: S1) dividing a source field and a target field according to different migration learning tasks, constructing a migration learning network, and initializing hyper-parameters of the migration learning network; S2) inputting respective data samples of the source domain and the target domain into a transfer learning network and carrying out forward propagation to obtain a network prediction label; training the whole network by using a stochastic gradient descent method according to the proposed loss function, completing updating of network parameters by using back propagation, and stopping training until the model converges or reaches the maximum number of iterations; S3)storing the network model and a training result; according to the target domain label prediction method based on the entropy minimization technology. By maximizing the distribution diversity of each batch of data prediction categories in the target domain, a common solution result occurring when only the entropy minimization technology is used is avoided, and the reliability of transfer learning is guaranteed.

Description

technical field [0001] The present invention relates to a learning system, specifically a deep transfer learning method, Background technique [0002] Supervised training of machine learning on a large amount of labeled data can achieve good performance and results. However, large labeled data sets are limited in number and application fields, and manual labeling of sufficient training data often requires high costs. Therefore, when faced with a target task where labeled data is scarce, how to use the existing labeled data in the source domain that is related to the target domain but obeys a different probability distribution to build an effective learner has a strong practical demand. [0003] Aiming at this problem, transfer learning method is usually used to solve it, that is, to train a discriminator to adjust the parameters of the transfer learning network, so that under the transfer learning network after parameter adjustment, the distribution offset between the data 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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/241
Inventor 吴晓富程磊张索非颜俊
Owner NANJING UNIV OF POSTS & TELECOMM
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
Eureka Blog
Learn More
PatSnap group products