Machine Learning in Quantum Sciences

Artificial intelligence is dramatically reshaping scientific research and is coming to play an essential role in scientific and technological development by enhancing and accelerating discovery across multiple fields. This book dives into the interplay between artificial intelligence and the quantum sciences; the outcome of a collaborative effort from world-leading experts. After presenting the key concepts and foundations of machine learning, a subfield of artificial intelligence, its applications in quantum chemistry and physics are presented in an accessible way, enabling readers to engage with emerging literature on machine learning in science. By examining its state-of-the-art applications, readers will discover how machine learning is being applied within their own field and appreciate its broader impact on science and technology. This book is accessible to undergraduates and more advanced readers from physics, chemistry, engineering, and computer science. Online resources include Jupyter notebooks to expand and develop upon key topics introduced in the book.

Anna Dawid is a research fellow at the Flatiron Institute, New York, with the Ph.D. in quantum physics awarded by the University of Warsaw and ICFO, Barcelona. Her research spans interpretable machine learning for scientific discovery, quantum simulations, and foundations of deep learning.

Alexandre Dauphin is VP quantum simulation at PASQAL, a neutral-atom quantum computing company. During his career, he has worked on a broad range of topics going from quantum simulation of many-body phases of matter to ML applied to physics and QML. He received the NJP early career award 2019, has been a member of the editorial board of NJP since 2020, and a member of ELLIS since 2021.

Julian Arnold is a theoretical physicist working at the interface between the quantum sciences, information theory, and machine learning. His research includes the design of methods for the automated detection of phase transitions and the application of differentiable programming to solve inverse design problems in quantum many-body physics.

Borja Requena develops machine learning algorithms for scientific applications. His contributions span multiple fields, from quantum to statistical and biophysics. Additionally, Borja has worked in high-tech companies such as Xanadu Quantum Technologies or Telefonica R&D, and he has been high ranked in machine learning and quantum computing competitions.

Alexander Gresch (Ph.D. Student at the universities of Düsseldorf and Hamburg) is a theoretical physicist specializing in mathematical and machine learning methods in the context of quantum technologies. This includes, in particular, the efficient and accurate read-out of hybrid quantum algorithms and the role of quantum data for machine learning.