US 12,236,077 B2
Methods and mechanisms for generating virtual knobs for model performance tuning
Jui-Che Lin, Taipei (TW); Yan-Jhu Chen, Taoyuan (TW); Chao-Hsien Lee, Taoyuan (TW); Shauh-Teh Juang, Zhubei (TW); Pengyu Han, Freemont, CA (US); and Wallace Wang, Hsinchu (TW)
Assigned to Applied Materials, Inc., Santa Clara, CA (US)
Filed by Applied Materials, Inc., Santa Clara, CA (US)
Filed on Apr. 25, 2022, as Appl. No. 17/728,021.
Prior Publication US 2023/0342016 A1, Oct. 26, 2023
Int. Cl. G06F 3/04847 (2022.01); G06F 3/0481 (2022.01); H01L 21/02 (2006.01)
CPC G06F 3/04847 (2013.01) [G06F 3/0481 (2013.01); H01L 21/02104 (2013.01)] 20 Claims
OG exemplary drawing
 
10. An electronic device manufacturing system, comprising:
a memory device; and
a processing device, operatively coupled to the memory device, to perform operations comprising:
receiving input data reflecting a feature related to a manufacturing process of a substrate;
providing a trained machine learning model trained based on the input data reflecting the feature;
generating a virtual knob for the trained machine learning model, wherein the virtual knob is configured to adjust a representative value of the trained machine learning model that is associated with the feature, to control a performance of the trained machine learning model; and
modifying, based on input received via the virtual knob, the trained machine learning model by adjusting the representative value.