Systematic review or meta-analysis of deep learning (DL) techniques and its integration into quantum physics applications

Students are strongly advised to go through the following guide [1] and example journal papers [2][3], so as to fully understand the reason behind doing systematic review/ meta-analysis and its process flow.

In layman’s terms, conducting systematic reviews or meta-analyses in the field of quantum physics with a focus on deep learning can provide valuable insights into the applications, performance, limitations, and opportunities of deep learning in quantum physics research. It can also help establish best practices, guidelines, and standards, and inform decision-making in practical quantum applications.

Specifically, we want to identify and/or create suitable and refined DL techniques/ models that can be integrated into quantum physics applications. For more details, please read the project description.

In this project, you will explore the following topic:

  • Systematic review or meta-analysis of DL techniques and implementations from different disciplines such as branches of physics, chemistry, biology and medicine, with an emphasis on finding suitable combination of DL techniques/models for common quantum physics applications.

    Typical examples are, and not exclusive to, optimizing the fidelity of quantum devices, optimizing the architecture/configuration of photonics components (waveguide/circuit/cavity), reconstructing quantum states and/or quantum channels, denoising quantum measurement data, optimizing quantum compiler, quantum circuits etc.

    Students should focus on one or at most two quantum physics applications to limit the research scale.

Students who are interested in the following DL project are assumed to have basic understanding of DL models, as well as a strong background in either quantum physics or computer science.
This project will be on an interviewing basis, as the finalized research statement has to be discussed and tailored for individual student.
Students are expected to go through literature search at least on the order of a few hundreds journal papers and studies, those who are strongly interested in reading a large number of papers and conducting thorough analysis are most welcomed.



[2] Grekousis, George. "Artificial neural networks and deep learning in urban geography: A systematic review and meta-analysis." Computers, Environment and Urban Systems 74 (2019): 244-256.
[3] Ma, Lei, et al. "Deep learning in remote sensing applications: A meta-analysis and review." ISPRS journal of photogrammetry and remote sensing 152 (2019): 166-177.