Bayesian optimization for Tuning Lithography Processes

Güler, Sila; Schoukens, Maarten; Perez, Taciano; Husakowski, Jerzy

doi:10.1016/j.ifacol.2021.08.464

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computer algorithms participating in this competition are Bayesian optimizations-a commonly used machine-learning method for expensive black-box functions [12][13][14] . This class of algorithms has been studied on other applications in the semiconductor industry [15][16][17] . Three diverse varieties of Bayesian optimizations were selected: (1) Algo1 using Markov chain Monte Carlo sampling 18 , a multivariate linear surrogate model to compensate for the high computation cost of the sampling, and an expected improvement (EI) function.…”

Section: Computer Algorithm Benchmarkingmentioning

confidence: 99%

Human–machine collaboration for improving semiconductor process development

Kanarik

Osowiecki

et al. 2023

Nature

View full text Add to dashboard Cite

One of the bottlenecks to building semiconductor chips is the increasing cost required to develop chemical plasma processes that form the transistors and memory storage cells1,2. These processes are still developed manually using highly trained engineers searching for a combination of tool parameters that produces an acceptable result on the silicon wafer3. The challenge for computer algorithms is the availability of limited experimental data owing to the high cost of acquisition, making it difficult to form a predictive model with accuracy to the atomic scale. Here we study Bayesian optimization algorithms to investigate how artificial intelligence (AI) might decrease the cost of developing complex semiconductor chip processes. In particular, we create a controlled virtual process game to systematically benchmark the performance of humans and computers for the design of a semiconductor fabrication process. We find that human engineers excel in the early stages of development, whereas the algorithms are far more cost-efficient near the tight tolerances of the target. Furthermore, we show that a strategy using both human designers with high expertise and algorithms in a human first–computer last strategy can reduce the cost-to-target by half compared with only human designers. Finally, we highlight cultural challenges in partnering humans with computers that need to be addressed when introducing artificial intelligence in developing semiconductor processes.

show abstract