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

Learning processing method, learning processing device, and program

A processing method and processing device technology, which are applied in the direction of nuclear methods, machine learning, biological models, etc., can solve the problems of low reliability and low classification similarity, and achieve the effect of improving reliability.

Inactive Publication Date: 2008-03-05
NAT INST OF INFORMATION & COMM TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, learning data with low classification similarity to the processed data may be used, and there is a disadvantage in that the reliability of extracting inherent representations is low.
[0012] Machine learning devices other than the above-mentioned genetic analysis system also have the same disadvantages

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
  • Learning processing method, learning processing device, and program
  • Learning processing method, learning processing device, and program
  • Learning processing method, learning processing device, and program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0041] FIG. 1 is a block diagram of a machine learning system according to Embodiment 1 of the present invention.

[0042] The machine learning system 10 of this embodiment has a similarity learning data generator 2 and a machine learning machine 5 .

[0043] The similarity learning data generator 2 has a similarity calculation unit 3 and a similarity learning data generation unit 4 .

[0044]The machine learning system 10 selects a problem to be solved (for example, problem data TD (Test Data: test data) ) of the similarity (Similarity) to meet the specified conditions of the partial set (such as similar learning data (Similarity Training Data) SSDq), and the selected similar learning data SSDq as the learning data of the machine learning machine 5, thereby seeking to improve the learning Speed ​​and learning accuracy.

[0045] In this way, in Embodiment 1, for example, from the learning data SDq, the similar learning data SSDq with high similarity (or high correlation) wit...

Embodiment approach 2

[0114] Embodiment 2 of the present invention is an embodiment of a machine learning system using the machine learning system of Embodiment 1 for learning processing of papers and the like.

[0115] In order to facilitate the understanding of the present invention, the correspondence between the components of Embodiment 2 and the components of the present invention will be described for reference only.

[0116] For example, the question data TD shown in FIG. 3 corresponds to the processed data of the present invention, and the learning data SDq corresponds to the learning data of the present invention.

[0117] The learned data Rq shown in FIG. 4 corresponds to the learned data of the present invention.

[0118] "Word" in Embodiment 2 corresponds to processing unit data of the present invention.

[0119] The similarity data BAq of the second embodiment corresponds to the similarity data of the present invention.

[0120] The index data TF(i, j) represented by the formula (6) ...

Embodiment approach 3

[0213] Embodiment 3 is an embodiment of a machine learning system using the machine learning system of Embodiment 1 for access control to content on the Internet.

[0214] FIG. 14 is a diagram for explaining a machine learning system 101 according to Embodiment 3 of the present invention. In the machine learning system 101 , the learning data generation unit 112 downloads a plurality of Web page data W1 stored in a server (not shown) on the Internet 111 .

[0215] The learning data generator 112 adds the tag data TG representing the classification (classification) of the content in the downloaded Web page data W1 according to predetermined rules, generates learning data (teacher data) SDq, and outputs it to the similar learning data selection Section 115.

[0216] As the tag data TG, for example, learning such as presence or absence of viewing restrictions, prohibition under restricted age, and violent behavior is indicated.

[0217] The similar learning data selection unit ...

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

There are provided a learning processing method and device capable of improving the learning speed and computer learning accuracy when computer learning is performed by using a plurality of learning data. A similar learning data generation unit (4) selects similar learning data SSDq having a high similarity with the data to be processed, from n learning data SDq. A computer learning device (5) performs computer learning by using the similar learning data SSDq.

Description

technical field [0001] The present invention relates to a learning processing method, a learning processing device, and a program for processing learning data using learning data. Background technique [0002] For example, the gene analysis system uses a database expressing genes (molecules) as nodes and the actions as links between the nodes for the actions between genes. [0003] When constructing such a database, for example, gene names are extracted from published papers and registered as nodes in the database. However, due to the large number of published papers, extracting gene names in a human-readable manner is a heavy burden. Therefore, it is conceivable to search various papers using a computer or the like, and to extract gene names from the retrieved papers. However, it is difficult to mechanically extract new gene names not registered by a computer. [0004] For example, the same problem arises when extracting inherent representations such as person names, pla...

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): G06N3/00G06N20/10
CPCG06N99/005G06N20/00G06N20/10
Inventor 土井晃一三森智裕福田安志实井仁村田真树
Owner NAT INST OF INFORMATION & COMM 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