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

Supervised learning optimization method under tensor mode and system thereof

A technology of supervised learning and optimization methods, applied in the field of supervised learning optimization methods and systems, which can solve problems such as local minimum, high algorithm time complexity, and dimension disaster

Inactive Publication Date: 2016-06-08
SHENZHEN INST OF ADVANCED TECH
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a supervised learning optimization method and system in tensor mode to solve the vector mode algorithm provided by the prior art, which occurs when processing tensor data, such as disaster of dimensionality, over-learning, small Sample and other problems, overcome the existing tensor mode algorithm, the algorithm of the present invention is to solve the limitations of the existing algorithm, such as the time complexity of the algorithm is very high, and often encounter problems such as local minimum

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
  • Supervised learning optimization method under tensor mode and system thereof
  • Supervised learning optimization method under tensor mode and system thereof
  • Supervised learning optimization method under tensor mode and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] figure 1 The implementation process of the supervised learning optimization method in the tensor mode provided by Embodiment 1 of the present invention is shown, and the details are as follows:

[0078] In step S101, an input training tensor dataset is received.

[0079] In the embodiment of the present invention, it is assumed that the training tensor data set is {Xm,ym|m=1,2.....M}, where X m Represents tensor input data, y m ∈{+1,-1} denotes a label.

[0080] Taking a grayscale image as an example, the sample points are stored in the form of a second-order tensor (matrix), and all sample points form the input data set in the form of a column vector. Similarly, the label set is also a column vector, and the value of each label The position corresponds to the position of the corresponding sample point.

[0081]

[0082] In step S102, the intra-class scatter matrix is ​​introduced into the objective function, so that the objective function maximizes the inter-cla...

Embodiment 2

[0139] figure 2 A specific structural block diagram of a supervised learning optimization system in tensor mode provided by Embodiment 2 of the present invention is shown. For convenience of description, only parts related to the embodiment of the present invention are shown. The supervised learning optimization system 2 under the tensor mode includes: a data receiving unit 21, an intra-class distribution introduction unit 22, a sub-problem optimization framework construction unit 23, a problem optimization framework construction unit 24, a dual problem acquisition unit 25, and a dual problem solving unit unit 26 , projection tensor calculation unit 27 , projection tensor decomposition unit 28 , back projection unit 29 , optimal projection tensor calculation unit 210 , decision function construction unit 211 and prediction unit 212 .

[0140] Wherein, the data receiving unit 21 is used to receive the input training tensor data set;

[0141] Intra-class dispersal introduction...

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 is suitable for the mode identification technology field and provides a supervised learning optimization method under a tensor mode and a system thereof. The method comprises the following steps of receiving an input training tensor data set; introducing a within-class scattering matrix into a target function so that the target function maximizes a between-class distance and simultaneously minimizes a within-class distance; constructing an optimization framework of a target function of an OPSTM subproblem; constructing an optimization framework of a target function of an OPSTM problem; solving a modified dual problem and outputting a Lagrangian optimal combination and an offset scalar b; calculating a projection tensor w*; calculating an optimal projection tensor w; according to the w and the b, constructing a decision function; carrying out rank decomposition on tensor data to be predicted and then inputting into the decision function so as to carry out prediction. In the invention, problems of a dimension curse, over learning, a small sample and the like generated when a vector mode algorithm is used to process the tensor data are overcome and a time-consuming alternative projection iteration process in an existing tensor mode algorithm is effectively avoided.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a supervised learning optimization method and system in a tensor pattern. Background technique [0002] With the advent of the big data era, the tensor expression of data has gradually become the mainstream. However, in the process of implementing the present invention, the inventors found that the prior art still uses vector mode algorithms to process tensor data. According to the point of view of the vector mode algorithm, feature extraction (vectorization) must be performed on the original data in the preprocessing stage. In this way, first, it is easy to destroy the unique spatial information and internal correlation of tensor data; second, there are too many model parameters, which may easily lead to Curse of dimensionality, over-learning, small samples, etc. [0003] Many tensor mode algorithms are the new darling of the times. However, the soluti...

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): G06K9/62
CPCG06F18/24
Inventor 王书强曾德威施昌宏卢哲
Owner SHENZHEN INST OF ADVANCED TECH
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