Leuven | More than two weeks ago
The goal of this research is to investigate continual learning adaptability in semiconductor process optimization and to establish the causal relationships (causal inference) in a data-centric approach.
As EUV based lithography gets adopted to keep scaling semiconductor devices in our chips, new metrology and inspection challenges arise. We need to measure these small dimensions fast but without losing accuracy and repeatability. Metrology and inspection are at the heart of process control. Without adequate metrology and inspection capability yields suffer. Conventional process and metrology tools, used in the industry, while generating a lot of data, do not always use them in feed-forward and feed -back cycles. However, there is a continuous need for better insight into process control by using this massive data. The sources of these data may range from tool process-logs to lab metrology to computational to FAB metrology inspection. Manual supervision, analysis and finding any relevant inter and /or intra-correlation between these monstrous data sources is nearly impossible and therefore requires better data analysis methods and advanced machine learning techniques. The goal of this project is to use data from the manufacturing tools and use them for building models for better process control and correlate with electrical performance of devices.
The student accepted for this position will learn conventional process flow and will be responsible to work collaboratively toward developing and applying “Continual (Machine) learning" based optimization algorithms with a goal to tackle the aforementioned challenges in terms of 1) Reducing computational cost, 2) reduce tool cycle time, 3) predictive process control approach in enabling advanced node semiconductor manufacturing. 4) Improving metrology data.
Machine learning applicability includes:
1. Brainstorm “Technical diligence” of the project: to meet desired performance and engineering timeline.
2. Tool Data Analysis: Collect data, analyse data, and suggest hypothesis with expert feedback loop.
3. To understand and establish the causal relationships (causal inference) in a data-centric approach.
4. To investigate continual learning adaptability and applications in semiconductor process optimization.
5. Image Processing applicability: Collect Image data (SEM/TEM/EDR/..), suggest ML based hypothesis to extract improved SEM based measurements.
6. Machine Learning Modelling – build from scratch or improve an existing algorithm for a given application task optimization o address or overcome metrology/process control-based tool limitations
7. Collaboration on patent/publications and presentations at international conferences/high-indexed journals
Required Specialized skillset(s):
Type of work: 60% for preparation and execution of experiments, 20% for data analysis, 20% for literature study.
Type of project: Combination of internship and thesis, Thesis.
Duration: 6 months. Can be extended based on performance.
Required degree: Master of Engineering Technology, Master of Science, Master of Engineering Science
Required background: Computer Science/Engineering, Electrotechnics/Electrical Engineering, Physics, Machine Learning/Artificial Intelligence.
Supervising scientist(s): For further information or for application, please contact: Sandip Halder (Sandip.Halder@imec.be) and Bappaditya Dey (Bappaditya.Dey@imec.be)
Our group website: https://sites.google.com/view/imec-ap-ml/home
Imec allowance will be provided.
Type of project: Thesis, Combination of internship and thesis
Duration: 6 months. Can be extended based on performance.
Required degree: Master of Engineering Technology, Master of Science, Master of Engineering Science
Required background: Computer Science, Electrotechnics/Electrical Engineering, Physics, Other
Supervising scientist(s): For further information or for application, please contact: Bappaditya Dey (Bappaditya.Dey@imec.be) and Sandip Halder (Sandip.Halder@imec.be)
Imec allowance will be provided.