文献类型：会议论文

英文题名：On Membership of Black-box or White-box of Artificial Neural Network Models

作者：Wu, Z. F.[1];Li, Jin[1];Cai, M. Y.[1];Zhang, W. J.[1,3];Lin, Y.[2]

机构：[1]East China Univ Sci & Technol, Complex & Intelligent Syst Res Ctr, Shanghai, Peoples R China;[2]Northeastern Univ, Dept Mech & Ind Engn, Boston, MA 02115 USA;[3]Univ Saskatchewan, Dept Mech Engn, Saskatoon, SK, Canada

会议论文集：IEEE 11th Conference on Industrial Electronics and Applications (ICIEA)

会议日期：JUN 05-07, 2016

会议地点：Hefei, PEOPLES R CHINA

语种：英文

外文关键词：ANN; black-box approach; white-box approach; fuzzy logics; modelling

摘要：Artificial Neural network (ANN) has been widely used in solving complex real world problems. It is commonly known as a black-box approach in the sense that examples (input and output pairs) are learned in the process of establishing an ANN model. However, there is a long debate in literature on whether ANN is a white-box or a black-box approach. In this article, we take a more conceptual view towards the nature of modelling with ANN, leading to a conclusion that ANN can be a black-box or grey-box approach, depending on the way to create an ANN model, in particular whether the knowledge of the problem and/or domain of the problem to be modeled by ANN is used in the creation of the ANN model. Another contribution of this paper is the outline of a methodology for designing ANN models, which is based on our proposed view in this paper that designing an ANN model is like designing a product and then the design theory and methodology for general products is learned to designing an ANN model.