Tham khảo tài liệu 'manufacturing the future 2012 part 7', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | 10 Zadehian Paradigms for Knowledge Extraction in Intelligent Manufacturing . Sharif Ullah and Khalifa H. Harib 1. Introduction Manufacturing is a knowledge-intensive activity. The knowledge underlying a specific manufacturing process or system is often extracted from a small set of experimental observations. To automate the knowledge extraction process various machine learning methods have been used Pham Afifi 2005 Monostori 2003 . Even though such methods are used a great deal of human intelligence knowledge extractor s judgment preference is required for getting good results Ullah Khalifa 2006 . As a result a machine learning method that is able to utilize human cognition as straightforwardly as possible seems more realistic for extracting knowledge in manufacturing. In fact human-assisted machine learning methods are in agreement with the modern concept of manufacturing automation how to support humans with computers rather than how to replace humans by computers Kals et al. 2004 . Thus for advanced manufacturing systems the machine learning methods wherein humans and computers compliment each other and the course of knowleldge extraction is determine by the human cognition rather than by a fully automated algorethemic approach is desirable. Artificial intelligence community has also started to recognize the need for human-assisted machining learning methods . human comprehensible machine learning methods Humans need to trust that intelligent systems are behaving correctly and one way to achieve such trust is to enable people to understand the inputs outputs and algorithms used as well as any new knowledge acquired through learning. As the use of machine learning increases in critical operations it is being applied increasingly in domains where the learning system s inputs and outputs must be understood or even modified by human operators. Dan Oblinger AAAI Technical Report WS-05-04 2005. 291 292 Manufacturing the Future Concepts Technologies Visions .
