基于概念网格构建神经网络的趣味性指数

IF 0.6 4区计算机科学 Q4 AUTOMATION & CONTROL SYSTEMS

Automation and Remote Control Pub Date : 2024-08-06 DOI:10.1134/s000511792403010x

M. M. Zueva, S. O. Kuznetsov

{"title":"基于概念网格构建神经网络的趣味性指数","authors":"M. M. Zueva, S. O. Kuznetsov","doi":"10.1134/s000511792403010x","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.</p>","PeriodicalId":55411,"journal":{"name":"Automation and Remote Control","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Interestingness Indices for Building Neural Networks Based on Concept Lattices\",\"authors\":\"M. M. Zueva, S. O. Kuznetsov\",\"doi\":\"10.1134/s000511792403010x\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3 data-test=\\\"abstract-sub-heading\\\">Abstract</h3><p>The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.</p>\",\"PeriodicalId\":55411,\"journal\":{\"name\":\"Automation and Remote Control\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2024-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Automation and Remote Control\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1134/s000511792403010x\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automation and Remote Control","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s000511792403010x","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

摘要解释神经网络性能的困难是一个众所周知的问题，正在引起广泛关注。基于概念网格的神经网络尤其是这一领域的一个有前途的方向。在构建神经网络时，形式概念的选择对其性能质量有关键影响。选择正式概念的标准可以基于趣味性指数，即使用某一指数值最高的概念来构建神经网络。本文研究了趣味性指数的选择对神经网络性能的影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Interestingness Indices for Building Neural Networks Based on Concept Lattices

查看原文本刊更多论文

Interestingness Indices for Building Neural Networks Based on Concept Lattices

Abstract

The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Automation and Remote Control 工程技术-仪器仪表

CiteScore

1.70

自引率

28.60%

发文量

审稿时长

3-8 weeks

期刊介绍： Automation and Remote Control is one of the first journals on control theory. The scope of the journal is control theory problems and applications. The journal publishes reviews, original articles, and short communications (deterministic, stochastic, adaptive, and robust formulations) and its applications (computer control, components and instruments, process control, social and economy control, etc.).