Project: ML projects at ASML
Description
ASML has recently re-confirmed there two projects; a couple more will likely be confirmed in the coming weeks
XAI in Exceptional Model Mining (--- update --- this project is taken by Yasemin Yasarol)
In the semiconductor industry there are different, diverse and unique failure modes that impact different steps and components of the microchip manufacturing process that can explain a particular anomaly in the quality of a microchip. You task will be to build a framework to find them and describe them using the available features or by new features to be created.
- Build a explainable exceptional model mining framework to find and describe failure modes
- Leverage all the available dataset: labeled and unlabeled
- Validate findings with domain experts
- Share results and progress on a regular basis
- Work from Veldhoven at least 4 days a week
- Deliverer documented code
Time2vec: convert multivariate time seriesto images (--- update --- this project is taken by Erdem Demir
Build an end-to-end framework to convert multivariate time series data (from machine sensors) to images, including model training, input data converting, and performance evaluating. The time series data come from hundreds of machine sensors, they are mainly from one class and there is a small set of labeled data.
- Build an end-to-end framework
- Design & train a deep learning model to capture features from multivariate time series and able to convert them into images
- Result evaluations must include at least two open datasets and one ASML dataset
- Mathematical explanations
- Share results and progress on a regular basis
- Work from Veldhoven at least 4 days a week
- Deliverer documented code
Details
- Supervisor
-
Mykola Pechenizkiy
- Secondary supervisor
-
TTtbc
- Interested?
- Get in contact