Search

To design a device that is robust to process-induced random variation, this study proposes a machine-learning-based predictive model that can simulate the electrical characteristics of FinFETs with process-induced line-edge roughness. This model, i.e., a Bayesian neural network (BNN) model with horseshoe priors (Horseshoe-BNN), can significantly reduce the simulation time (as compared to the conventional technology computer-aided design (TCAD) simulation method) in a sufficiently accurate manner. Moreover, this model can perform autonomous model selection over the most compact layer size, which is necessary when the amount of data must be limited. The mean absolute percentage error for the mean and standard deviation of the drain-to-source current $\left ({\mathrm {I}_{\mathrm {DS}} }\right)$ were ~0.5% and ~6%, respectively. By estimating the distribution of the current-voltage characteristics, the distributions of the other device metrics, such as off-state leakage current and threshold voltage, can be estimated as well.

The color filter required for manufacturing a CMOS image sensor was redeveloped to optimize its optical uniformity. An in-depth study of the three-dimensional (3D) coating process and how it gives rise to various radial-shaped striation patterns was conducted. These radial-shaped striation patterns were systematically investigated with reference to two types of patterns: the orthogonal type found only at the orthogonal edges of the wafer and the diagonal type found mostly at the corner of each quadrant. The formation of the orthogonal pattern was based on the wide standing wave created by the incident force of the spreading color photoresist (PR) and the reflective force from the bump pads acting as coating barriers. The diagonal pattern was found to be generated by the turbulent wakes created behind the bump pads by the drag force, which interfered with the coating flow. An in-depth study using Ansys CFX software and an in-line inspection tool revealed that lowering the viscosity of the color PR material is a key factor for improving the phenomenon whereby the 3D striation patterns of the orthogonal and diagonal types are formed. Based on this finding, it was possible to drastically reduce the formation of the 3D striation patterns by decreasing the viscosity of the material comprising each color PR. This study provides not only an empirical and theoretical understanding of the 3D color PR coating mechanism, but also guidelines for future color filter processes.