Title :
Applying machine learning to semiconductor manufacturing
Author :
Irani, Keki B. ; Cheng, Jie ; Fayyad, Usama M. ; Qian, Zhaogang
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Michigan Univ., Ann Arbor, MI, USA
Abstract :
The generalized ID3 (GID3) algorithm, which takes a training set of experimental data and produces a decision tree that predicts the outcome of future experiments under various, more general conditions, is described. The tree can then be translated into a set of rules for an expert system. Two extensions to GID3MmRIST, and KARSM-that deal with the problems of noisy data and the limited availability of training data are discussed. The application of GID3 to reactive ion etching manufacturing process diagnosis and optimization and to knowledge acquisition for an expert system is described.<>
Keywords :
computer integrated manufacturing; expert systems; knowledge acquisition; learning (artificial intelligence); GID3; KARSM; decision tree; expert system; generalized ID3; knowledge acquisition; machine learning; noisy data; optimization; reactive ion etching manufacturing process diagnosis; semiconductor manufacturing; training set; Decision trees; Diagnostic expert systems; Etching; Knowledge acquisition; Machine learning; Machine learning algorithms; Manufacturing processes; Semiconductor device manufacture; Semiconductor device noise; Training data;
Journal_Title :
IEEE Expert
