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.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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 ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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