153
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      scite_
       
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Automatic creation of training set for neural networks aimed to detect patent 
      users. Automatic testing of the neural network performance.

      Preprint
      In review
      research-article
        1 ,
      ScienceOpen Preprints
      ScienceOpen
      Bookmark

            Abstract

            This article is the results of the research, aimed to train, test and use custom neural network effortlessly, without spending huge amountof time and efforts to prepare special training set or to test trained neural network performance. I have submitted an algorithms and the theory used for for automatic creation of the training set as well as an algorithms and the theory used for neural network automatic testing. Atvthe final chapter of the article I have provided results of ner recognition, performed by neural network, trained on automatically created training set.

            Content

            Author and article information

            Journal
            ScienceOpen Preprints
            ScienceOpen
            20 January 2023
            Affiliations
            [1 ] University of Pisa
            Author notes
            Author information
            https://orcid.org/0000-0002-8088-0671
            Article
            10.14293/S2199-1006.1.SOR-.PPUEPH0.v1
            1750c5c0-8b87-401e-ad3d-a1a13273d43d

            This work has been published open access under Creative Commons Attribution License CC BY 4.0 , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Conditions, terms of use and publishing policy can be found at www.scienceopen.com .

            History
            : 20 January 2023
            Categories

            The data that support the findings of this study are available from https://github.com/airermakova/webPortal but restrictions apply to the availability of these data, which were used under license for the current study, and so are not publicly available. Data are however available from the authors upon reasonable request and with permission of https://github.com/airermakova/webPortal.
            Software engineering,Artificial intelligence

            Comments

            Comment on this article