Samsung Electronics Co., Ltd.

Gwangnae Gil

Jonghyun Lee

Seyoung Park

Sola Woo

A method of operating an electrical test prediction apparatus includes determining a relationship between first electrical test (ET) data, corresponding to at least one shot region comprising a subset of a plurality of semiconductor chips of a wafer, and electrical die sorting (EDS) data, obtained by measuring a state of each chip on the wafer by a testing device, and predicting second ET data, corresponding to an region of the wafer other than the at least one shot region by performing machine learning on the relationship.

Computing devices for predicting electrical tests, electrical test prediction apparatuses having the same, and operating methods thereof

To predict characteristics of a semiconductor device, a simulation current-voltage curve of the semiconductor device is generated using compact models where each compact model generates simulation result data by performing a simulation based on device data. The simulation result data indicate characteristics of semiconductor devices corresponding to the device data. The compact models respectively corresponding to process data and semiconductor products. Simulation reference points on the simulation current-voltage curve are extracted. Basic training data corresponding to a combination of the simulation reference points and the simulation current-voltage curve are generated. A deep learning model is trained based on the basic training data such that the deep learning model outputs a prediction current-voltage curve. A target prediction current-voltage curve is generated based on the deep learning model and target reference points corresponding to the target semiconductor product. The deep learning model is a generative adversarial network.

Method of predicting characteristic of semiconductor device and computing device performing the same

Measurement data are produced by measuring characteristics of a semiconductor device. Target parameters are selected among a plurality of parameters of a device model where the device model is configured to perform a simulation based on device data and output simulation result data indicating the characteristics of the semiconductor device. Initial value sets corresponding to different combinations of initial values of the target parameters are selected. Local minimum values are determined based on reinforcement learning. Each local minimum value corresponds to a minimum value of a difference between the measurement data and the simulation result data with respect to each initial value set. Optimal values of the target parameters are determined based on the plurality of local minimum values. The device model capable of precisely predicting characteristics of the semiconductor device is generated by determining the parameters of the device model using the optimization scheme based on the reinforcement learning.

Growing community of inventors

Yongin-si, South Korea

Gwangnae Gil