US Patent Application 17824282. METHODS AND MECHANISMS FOR PREVENTING FLUCTUATION IN MACHINE-LEARNING MODEL PERFORMANCE simplified abstract
METHODS AND MECHANISMS FOR PREVENTING FLUCTUATION IN MACHINE-LEARNING MODEL PERFORMANCE
Organization Name
Inventor(s)
Chao-Hsien Lee of Taoyuan (TW)
Shauh-Teh Juang of Zhubei (TW)
METHODS AND MECHANISMS FOR PREVENTING FLUCTUATION IN MACHINE-LEARNING MODEL PERFORMANCE - A simplified explanation of the abstract
This abstract first appeared for US patent application 17824282 titled 'METHODS AND MECHANISMS FOR PREVENTING FLUCTUATION IN MACHINE-LEARNING MODEL PERFORMANCE
Simplified Explanation
The patent application describes an electronic device manufacturing system that uses input data to analyze and improve the manufacturing process of a substrate.
- The system generates a characteristic sequence that defines the relationship between different manufacturing parameters.
- It then determines the relationship between variables related to the manufacturing process and the characteristic sequence.
- Based on this relationship, the system assigns a weight to the feature being analyzed.
- The system uses this weighted feature to train a machine-learning model, which can then be used to optimize the manufacturing process.
Original Abstract Submitted
An electronic device manufacturing system configured to receive, by a processor, input data reflecting a feature related to a manufacturing process of a substrate. The manufacturing system is further configured to generate a characteristic sequence defining a relationship between at least two manufacturing parameters, and determine a relationship between one or more variables related to the feature and the characteristic sequence. The manufacturing system is further configured to determine a weight based on the determined relationship and apply the weight to the feature. The manufacturing system is further configured to train a machine-learning model in view of the weighted feature.