• Corpus ID: 233033553

A Novel Approach for Semiconductor Etching Process with Inductive Biases

  title={A Novel Approach for Semiconductor Etching Process with Inductive Biases},
  author={Sanghoon Myung and Hyunjae Jang and Byungseon Choi and Jisu Ryu and Hyuk Kim and Sang Wuk Park and Changwook Jeong and Daesin Kim},
The etching process is one of the most important processes in semiconductor manufacturing. We have introduced the state-of-the-art deep learning model to predict the etching profiles. However, the significant problems violating physics have been found through various techniques such as explainable artificial intelligence and representation of prediction uncertainty. To address this problem, this paper presents a novel approach to apply the inductive biases for etching process. We demonstrate… 

Figures from this paper

Restructuring TCAD System: Teaching Traditional TCAD New Tricks
The proposed algorithm predicts three-dimensional TCAD simulation in real-time while capturing a variance, enables deep learning and TCAD to complement each other, and fully resolves convergence errors.
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning
PAC-Net is proposed, a simple yet effective approach for transfer learning based on pruning that achieves state-of-the-art performance by a large margin and specifies attributes (38 attributes) for model to learn generic knowledge regrading datasets.


Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
This work proposes an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates.
A Unified Approach to Interpreting Model Predictions
A unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), which unifies six existing methods and presents new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
LIME is proposed, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning aninterpretable model locally varound the prediction.
Attention is All you Need
A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.
Deep trench isolated CMOS devices
A deep (5-6 microns) trench isolation process which permits minimum feature size spacing between n- and p-channel devices in bulk CMOS is described. Susceptibility to latch-up at 1.2 microns n-p
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
A new theoretical framework is developed casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes, which mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy.
Sentaurus Topography 3D User Guide
  • 2016