Presentation Information
[7p-S202-5]Machine learning model design focusing on error accumulation structure in multi-stage semiconductor manufacturing process
〇Takumi Yamada1, Kentaro Kutsukake1,2, Shunta Harada1,2, Toru Ujihara1,2 (1.Grad. Sch. Eng., Nagoya Univ., 2.IMaSS Nagoya Univ.)
Keywords:
error accumulation,machine learning,multi-stage process
When machine learning is applied to a multi-stage process such as a semiconductor manufacturing process, it is known that the prediction errors that occur at each stage accumulate, and the final prediction accuracy declines, but effective methods for suppressing these errors are still under study. In this study, we focused on the structure of the input distribution, analyzed the causes of error accumulation, and examined methods to suppress the accumulation of errors.