Biography
My name is Yinchong Yang (杨寅翀). I am a senior key expert of robust AI at Siemens. My current research interests include the quantification and certification of AI robustness and uncertainty. I’m also interested in tensor decomposition methods in machine learning, such as tensorized neural networks and relational learning from tensor data.
Interests
- Machine learning and artificial intelligence.
- Uncertainty, robustness quantification and certification in machine learning.
- Tensor decomposition and its application in machine learning
Education
-
Dr. rer. nat. in computer science, 2018
LMU Munich
-
M.Sc. in statistics, 2015
LMU Munich
-
B.Sc. in statistics, 2012
LMU Munich
Skills
Machine Learning
90%
Statistical Modeling
80%
Experience
Senior Key Expert for robust AI
Siemens AG
Research and Development in:
- Robustness quantification and certification in machine learning.
- Other methods for Trustworthy AI in industry, including uncertainty and explainability.
Research Scientist
Siemens AG
Research and Development in:
- Modern AI (deep learning), with focus on computer vision tasks.
- Uncertainty-aware knowledge graph modeling.
Doctoral candidate
Siemens AG
Research in clinical decision modeling:
- Unstructured data.
- Robustness and explainable models.
Intern, working student and master thesis
PwC Deutschland
Research and development in Big Data:
- Parallel algorithms and development frameworks.
- Anomaly analysis in financial data.
Working student and master thesis
Infineon
Support in developing statistical methods for quality management.
Accomplishments
Probabilistic Deep Learning with TensorFlow 2
See certificate
Google IT Automation with Python Specialization
See certificate
Bayesian Methods for Machine Learning
See certificate
Convolutional Neural Networks
See certificate
Sequence Models
See certificate
Improving Deep Neural Networks -Hyperparameter Tuning, Regularization and Optimization
See certificate
Selected Publications
Quickly discover relevant content by filtering publications.
(2021).
Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning.
In IEEE ICHI.
(2021).
Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models.
In MLHC.
(2019).
Categorical EHR Imputation with Generative Adversarial Nets.
In IEEE ICHI.
(2018).
Explaining Therapy Predictions with Layer-wise Relevance Propagation in Neural Networks.
In IEEE ICHI.
(2018).
Enhancing representation learning with tensor decompositions for knowledge graphs and high dimensional sequence modeling.
Dissertation at LMU Munich.
(2017).
Modeling Progression Free Survival in Breast Cancer with Tensorized Recurrent Neural Networks and Accelerated Failure Time Model.
In MLHC.
(2017).
Predictive Modeling of Therapy Decisions in Metastatic Breast Cancer with Recurrent Neural Network Encoder and Multinomial Hierarchical Regression Decoder.
In IEEE ICHI.
(2017).
Tensor-Train Recurrent Neural Networks for Video Classification.
In ICML.
