Browsing by Author "Akbar, Chandni"

Now showing 1 - 4 of 4

Analytics-statistics mixed training and its fitness to semisupervised manufacturing
(2019-08-13)
Parashar, Parag
;
Chen, Chun Han
;
Akbar, Chandni
;
Fu, Sze Ming
;
Rawat, Tejender S.
While there have been many studies using machine learning (ML) algorithms to predict process outcomes and device performance in semiconductor manufacturing, the extensively developed technology computer-aided design (TCAD) physical models should play a more significant role in conjunction with ML. While TCAD models have been effective in predicting the trends of experiments, a machine learning statistical model is more capable of predicting the anomalous effects that can be dependent on the chambers, machines, fabrication environment, and specific layouts. In this paper, we use an analytics-statistics mixed training (ASMT) approach using TCAD. Under this method, the TCAD models are incorporated into the machine learning training procedure. The mixed dataset with the experimental and TCAD results improved the prediction in terms of accuracy. With the application of ASMT to the BOSCH process, we show that the mean square error (MSE) can be effectively decreased when the analytics-statistics mixed training (ASMT) scheme is used instead of the classic neural network (NN) used in the baseline study. In this method, statistical induction and analytical deduction can be combined to increase the prediction accuracy of future intelligent semiconductor manufacturing.
Intelligent Manufacturing: TCAD-Assisted Adaptive Weighting Neural Networks
(2018-01-01)
Huang, Chien Y.
;
Fu, Sze M.
;
Parashar, Parag
;
Chen, Chun H.
;
Akbar, Chandni
Using machine intelligence on device and process performance prediction is an emerging methodology in the IC industry. While semiconductor technology computer-aided design (TCAD) has been researched and developed for over 30 years, it should contribute to or be used in conjunction with machine learning algorithms in solution finding procedure. Here, we propose an adaptive weighting neural network (AWNN) model that combines the advantages of statistical the machine learning model and the physical TCAD model. Using aspect ratio dependent etching as an example, our proposed AWNN outperforms conventional artificial neural network in terms of mean square errors in the test set where 5-10 times reduction is observed. The effectiveness of the TCAD AWNN model can be especially effective in the case of sampling over a vast sample space since the under-sampling problem can be compensated by the TCAD model. The large and nearly unbounded sample space is very common in IC technology, where cascaded and repeated process steps exist (similar to 150 process steps and similar to 20 masks for 90-nm CMOS process).
Intelligent Photolithography Corrections Using Dimensionality Reductions
(2019-10-01)
Parashar, Parag
;
Akbar, Chandni
;
Rawat, Tejender S.
;
Pratik, Sparsh
;
Butola, Rajat
With the shrinking of the IC technology node, optical proximity effects (OPC) and etch proximity effects (EPC) are the two major tasks in advanced photolithography patterning. Machine learning has emerged in OPC/EPC problems because conventional optical-solver-based OPC is time-consuming, and there is no physical model existing for EPC. In this work, we use dimensionality reduction (DR) algorithms to reduce the computation time of complex OPC/EPC problems while the prediction accuracy is maintained. Also, we implement a pure machine learning approach where the input masks are directly mapped to the output etched patterns. While one photolithographic mask can generate many experimental patterns at once, our pure ML-based approach can shorten the trial-and-error period in the photolithographic correction. Additionally, we demonstrate the automation in SEM images preprocessing using feature detection, and this facilitates intelligent manufacturing in semiconductor processing. The input vector dimensions are effectively reduced by two orders of magnitude while the observed mean squared error is not affected significantly. The computation runtime is reduced from 4804 s of the baseline calculation to 10 s-200 s The MSE values changed from the baseline 0.037 to 0.037 for singular value decomposition (SVD), to 0.039 for independent component analysis (ICA), and to 0.035 for factor analysis (FA).
Physics-Prior Bayesian Neural Networks in Semiconductor Processing
(2019-01-01)
Chen, Chun Han
;
Parashar, Parag
;
Akbar, Chandni
;
Fu, Sze Ming
;
Syu, Ming-Ying
With the fast scaling-down and evolution of integrated circuit (IC) manufacturing technology, the fabrication process becomes highly complex, and the experimental cost of the processes is significantly elevated. Therefore, in many cases, it is very costly to obtain a sufficient amount of experimental data. To develop an efficient method to predict the results of semiconductor experiments with a small amount of known data, we use a novel method based on Bayesian framework with the prior distribution constructed by technology computer-aided-design (TCAD) physical models. This method combines the advantages of statistical models and physical models in the aspect that TCAD can provide visionary guidance on an experiment when a limited amount of experimental data is available, and a machine learning model can account for subtle anomalous effects. Specifically, we use aspect ratio dependent etching (ARDE) phenomenon as an example and use variational inference with Kullback-Leibler divergence minimization to achieve the approximation to the posterior distribution. The relation between etching process input parameters and etching depth is learned using the Bayesian neural network with TCAD priors. Using this method with 35 neurons per hidden layer, mean square error (MSE) in the test set is reduced from 0.2896 to 0.0175, 0.058 to 0.0183, 0.0563 to 0.0188, 0.058 to 0.019 for partition =10, 20, 30, 40, respectively, reference to the baseline BNN where a regular normal distribution prior with zero mean and unity standard deviation N(0,1) is used.