Skip to Content
Artificial Intelligence for the analytics of quantum devices
We are looking for highly motivated students with a strong background in nanoscience, physics, or computational sciences. We provide state-of-the-art facilities in a cutting-edge research field. For more information, please contact Dr. Mickael Perrin (Mick-ael.Perrin@empa.ch). For applications, please send a short motivation (including educa-tional background and exam grades).
Unsupervised machine learning (ML), and in particular data clustering, is a powerful ap-proach for the analysis of datasets and identification of characteristic features occurring throughout a dataset. It is gaining popularity across scientific disciplines and is particular-ly useful for applications without a priori knowledge of the data structure. In our lab, we have developed several ML approaches for the classification of univariate measurements and apply it to the field of nanoelectronics and spectroscopy. This allows us to identify meaningful structures in data sets, providing physically relevant information about the system under study.
In this master project, the student will develop novel feature extraction methods suited for nanoscale devices with as aim the improvement of the classification accuracies. One of the paths to be explored will be the investigation of the feature extraction capabilities of convolutional neural networks. The validation of the models will occur on experimental datasets with known labels and on synthetic data. For the generation of synthetic data, the use of generative adversarial networks (GANs) will be explored. The experimental da-tasets will be acquired either in the lab or provided via collaborators.
The student will learn:
- Multiple machine learning methods (data classification, GANs, convolutional neu-ral networks, …).
- Physics of nanoscale quantum devices.
- Measurements on quantum devices.
- High-performance computing.