TY - GEN
T1 - Stochastic Feed-forward Attention Mechanism for Reliable Defect Classification and Interpretation
AU - Lee, Jiyoon
AU - Mok, Chunghyup
AU - Kim, Sanghoon
AU - Moon, Seokho
AU - Kim, Seo Yeon
AU - Kim, Seoung Bum
N1 - Funding Information:
Acknowledgments. This research was supported by the Brain Korea 21 FOUR and the IITP grant funded by the MSIT (No.2021–0-00034).
Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Defect analysis in manufacturing systems has been crucial for reducing product defect rates and improving process management efficiency. Recently, deep learning algorithms have been widely used to extract significant features from intertwined and complicated manufacturing systems. However, typical deep learning algorithms are black-box models in which the prediction process is difficult to understand. In this study, we propose a stochastic feed-forward attention network that consists of input feature level attention. The stochastic feed-forward attention network allows us to interpret the model by identifying the input features, dominant for prediction. In addition, the proposed model uses variational inferences to yield uncertainty information, which is a measure of the reliability of the interpretations. We conducted experiments in the field of display electrostatic chuck fabrication process to demonstrate the effectiveness and usefulness of our method. The results confirmed that our proposed method performs better and can reflect important input features.
AB - Defect analysis in manufacturing systems has been crucial for reducing product defect rates and improving process management efficiency. Recently, deep learning algorithms have been widely used to extract significant features from intertwined and complicated manufacturing systems. However, typical deep learning algorithms are black-box models in which the prediction process is difficult to understand. In this study, we propose a stochastic feed-forward attention network that consists of input feature level attention. The stochastic feed-forward attention network allows us to interpret the model by identifying the input features, dominant for prediction. In addition, the proposed model uses variational inferences to yield uncertainty information, which is a measure of the reliability of the interpretations. We conducted experiments in the field of display electrostatic chuck fabrication process to demonstrate the effectiveness and usefulness of our method. The results confirmed that our proposed method performs better and can reflect important input features.
KW - Bayesian neural network
KW - Defect prediction
KW - Electrostatic chuck fabrication process
KW - Explainable artificial intelligence
KW - Feed-forward attention mechanism
UR - http://www.scopus.com/inward/record.url?scp=85137980913&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-16072-1_11
DO - 10.1007/978-3-031-16072-1_11
M3 - Conference contribution
AN - SCOPUS:85137980913
SN - 9783031160714
T3 - Lecture Notes in Networks and Systems
SP - 148
EP - 158
BT - Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1
A2 - Arai, Kohei
PB - Springer Science and Business Media Deutschland GmbH
T2 - Intelligent Systems Conference, IntelliSys 2022
Y2 - 1 September 2022 through 2 September 2022
ER -