Machine learning and the physical sciences
By Giuseppe Carleo, I. Cirac, Kyle Cranmer, Laurent Daudet, Maria Schuld, Naftali Tishby, Leslie Vogt-Maranto, Lenka Zdeborov'a. 2019
1,895 citations recorded by the source corpus.
Machine learning (ML) encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences. This includes conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields. After giving a basic notion of machine learning methods and principles, examples are described of how statistical physics is used to understand methods in ML. This review then describes applications of ML methods in particle physics and cosmology, quantum many-body physics, quantum computing, and chemical and material physics. Research and development into novel computing architectures aimed at accelerating ML are also highlighted. Each of the sections describe recent successes as well as domain-specific methodology and challenges.
Subfields: Artificial Intelligence, Atomic and Molecular Physics, and Optics, Materials Chemistry, AI for Physical Sciences
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hsin-Yuan Huang
- Mark Saffman
- Mikhail D. Lukin
- John Preskill
- Alán Aspuru-Guzik
- Sophia E. Economou
- Richard Kueng
- Kristan Temme
In Atomic and Molecular Physics, and Optics
- Mark Saffman
- Mikhail D. Lukin
- Hsin-Yuan Huang
- I. Bloch
- John Preskill
- E. Demler
- Richard Kueng
- Sophia E. Economou
In Materials Chemistry
- Florian Hase
- Pascal Friederich
- Jonathan Shlomi
- Alán Aspuru-Guzik
- Hartmut Löwen
- Jun Ye
- Mikhail D. Lukin
- E. Filipov
In AI for Physical Sciences
- Alán Aspuru-Guzik
- Hartmut Löwen
- E. Altman
- Michael te Vrugt
- Marco F. Duarte
- Peter W. Battaglia
- Andrew M. Weiner
- Jochen Garcke
Citations in the corpus
- Explainable Machine Learning for Scientific Insights and Discoveries (2019, background): “A review on the manifold recent research topics in the physical sciences is given by [109], with applications in particle physics and cosmology, quantum many-body physics, quantum computing, and chemical and material physics.”
- Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation (2019, methodology): “d to the chemical domain, but the method can also be applied in various scientific design questions with syntactic and semantic constraints. For example, many questions in machine learning for physics [48] have similar character and could benefit from robust representations enforced by SELFIES. Two sp”
- An introduction to deep generative modeling (2021, background): “Those include new scientific applications of DGMs, for example, in physics and computational chemistry [8, 33, 6].”
- 2022 Roadmap on integrated quantum photonics (2021, background): “Among the most popular class of machine learning algorithms are discriminative artificial neural networks, which specify nonlinear mappings between input and output variables using matrix multiplication, neuron-based processing, and nonlinear activation functions [267].”
- Tailoring Structure‐Borne Sound through Bandgap Engineering in Phononic Crystals and Metamaterials: A Comprehensive Review (2022, positive): “These methods focus on acquiring vast collection of training data and utilizing artificial neural networks to classify them and arrive at the required parameters for the desired goal [461].”
- Classical dynamical density functional theory: from fundamentals to applications (2020, methodology): “ef. [793]. More recently, machine-learning methods have been used to approximate classical density functionals in DFT [794]. Machine learning is already successfully applied in quantum DFT (see Refs. [795,796] for reviews). A variety of authors have discussed the discretization and integration of DD”
- Quantum Simulators: Architectures and Opportunities (2019, methodology): “[111] Giuseppe Carleo, Ignacio Cirac, Kyle Cranmer, Laurent Daudet, Maria Schuld, Naftali Tishby, Leslie Vogt-Maranto, and Lenka Zdeborov.”
- Variational Quantum Circuits for Deep Reinforcement Learning (2019, background): “…of quantum computing, many machine learning work start to consider techniques of quantum mechanics such as quantum many-body physics[8, 9, 10], phase-transitions [11], quantum control [12, 13], and quantum error correction [14, 15] because those methods can be used for machine learning…”
- Quantum optimal control in quantum technologies. Strategic report on current status, visions and goals for research in Europe (2022, background): “2 Quantum optimal control vs machine learning approaches Machine learning is a field of computer science which has been attracting much attention in many areas in physics [113, 309, 413].”
- Graph neural networks in particle physics (2020, background): “[2] Giuseppe Carleo, Ignacio Cirac, Kyle Cranmer, Laurent Daudet, Maria Schuld, Naftali Tishby, Leslie Vogt-Maranto, and Lenka Zdeborová.”