模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2007, Vol. 20 Issue (1): 72-84    DOI:
Surveys and Reviews Current Issue| Next Issue| Archive| Adv Search |
How to Add Transparency to Artificial Neural Networks
HU BaoGang, WANG Yong, YANG ShuangHong, QU HanBing
Institute of Automation, Chinese Academy of Sciences, Beijing 100080
Graduate School, Chinese Academy of Sciences, Beijing 100080

Download: PDF (782 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The main issue about “black box” inherent in artificial neural networks (ANN’s) is discussed. Adding transparency is well recognized to be an effective solution to dealing with this problem. Significant benefits are obtained through using this approach, such as providing a certain degree of comprehensive power, decreasing model size, speeding learning process and improving generalization capability. A hierarchical classification is applied to the existing approaches for better understanding of their intrinsic features and limitations. The first level of classification is made by two strategies: building prior knowledge into neural networks; extracting rules embedded within networks. Most of important approaches are introduced and compared in detail with further classifications within each strategy. Finally, the personal perspectives to the studies of machine learning are presented. Other objective functions are suggested for the extension of studies, such as performancetocost ratio and transparency. The study of increasing transparency to ANN’s is considered as the most fundamental and direct solution to the other existing issues. A new machine learning approach called Knowledge Increasing via Feedback is proposed.
Key wordsMachine Learning      Artificial Neural Networks      Prior Knowledge      Induction      Deduction      Black Box     
Received: 27 July 2006     
ZTFLH: TP183  
  TP181  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
HU BaoGang
WANG Yong
YANG ShuangHong
QU HanBing
Cite this article:   
HU BaoGang,WANG Yong,YANG ShuangHong等. How to Add Transparency to Artificial Neural Networks[J]. , 2007, 20(1): 72-84.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2007/V20/I1/72
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn