Mathematics | Data Science Internship (non-thesis): Detection of Degradation Patterns

Introduction

Are you interested in Machine Learning and have coding skills in Python an MATLAB? Then this internship could be interesting for you!

Background Information

The optical column is the heart of the EUV system, a technological miracle. ASML’s EUV machines push Moore’s law forward, enabling new technology waves that improve everyone’s life. Together with our partner Zeiss the Optical Column department pushes the EUV optical technology to the limit. By this we unlock imaging capabilities that seem impossible today.

The EUV Illumination group is part of the Optical Column department. In the EUV Illumination group we are responsible for the design and qualification of the illumination system in the EUV scanners.

Your Assignment

This project aims to create an algorithm that can automatically detect and quantify the degradation of optical surfaces. The algorithm uses principal component analysis (PCA) and independent component analysis (ICA) to extract the features of degradation from the optical images. The project will involve the following steps:

• Using a large dataset of optical images;
• Preprocessing the images to remove outliers and reduce noise;
• Applying PCA to reduce the dimensionality of the images and obtain the principal components (PCs) that capture the most variance in the data;
• Applying ICA to further decompose the PCs into independent components (ICs) that capture the most non-Gaussianity in the data;
• Training a regressor, such as a neural network or a linear model, on the ICs to learn to predict the degree of degradation in optical surfaces based on some metrics;
• Evaluating the performance of the regressor on a test set of optical surface transmission images and comparing it with other methods of degrading mirror detection (if any);
• Furthermore, analyze the different toolkits available and provide recommendations for degrading optical surface pattern detection. 

The expected outcomes of this project are:

• A working prototype of an automated degrading pupil pattern detection algorithm that can accurately identify and measure the level of degradation in optical surfaces using PCA and ICA analysis;
• A report documenting the methodology, results, and challenges of the project;
• A presentation demonstrating the functionality and effectiveness of the algorithm.

Your Profile

To be the perfect match for this internship you:

• Are studying Engineering, Mathematics, or a related field;
• Have a high affinity towards machine learning;
• Have knowledge in Python and MATLAB;
• Have knowledge on statistics, linear algebra, PCA, an ICA.

This is a master apprentice internship lasting 6 months for 5 days per week (3 of which at the ASML premises), starting as soon as possible.

Please note that we can only consider students for this internship who are enrolled at an university during the whole internship period.

Other Information

Change the world – one nanometer at a time
Become an intern at a Dutch company that’s a global industry leader. You’ll gain valuable experience in a highly innovative environment – one that sparks your imagination and creativity. In addition to a monthly internship allowance of maximum €600 (plus a possible housing and free public transport), you’ll get practical guidance from experts in the field and the chance to work in and experience a dynamic team environment.

ASML: be part of progress
ASML is a high-tech company headquartered in the Netherlands. We manufacture the complex lithography machines that chipmakers use to produce integrated circuits, or computer chips. What we do is at the heart of all the electronic devices that keep us informed, entertained and connected. Every day, you use electronics that simply wouldn’t exist without our machines.

Behind ASML’s innovations are engineers who think ahead. The people who work at our company include some of the most creative minds in physics, electrical engineering, mathematics, chemistry, mechatronics, optics, mechanical engineering, and computer science and software engineering.

We believe we can always do better. We believe the winning idea can come from anyone. We love what we do – not because it’s easy, but because it’s hard.

Students: getting ready for real-world R&D
We’re a global team of about 39,000 people of 140 different nationalities and counting. Headquartered in Europe’s top tech hub, the Brainport Eindhoven region in the Netherlands, our operations are spread across Europe, Asia and the US.

In such an environment, your colleagues may be sitting next door, or they could be thousands of kilometers away in a different country – or even working for a different company.

An internship at ASML is the opportunity to get to know not only the world of industrial-strength R&D, but yourself – you’ll discover just what excites you most. Will you design a part of the machine, or make sure it gets built to the tightest possible specifications? Will you write software that drives the system to its best performance, or work side-by-side with the engineers of our customers in a fab, optimizing a system to the requirements of the customer?

How will you be part of progress?