Neural networks controlling superconducting quantum circuits

The ARTEMIS project aims at establishing and commercializing a radically new neural-networks-based quantum control approach. It will use reinforcement learning on real time experimental observations in order to overcome today’s main challenges in quantum computing – quantum error correction and optimal control. In this project we will develop a quantum controller that incorporates real-time neural networks capable of generating controls based on measurement outcomes during the run time of quantum circuits. Such neural networks are expected to enhance accuracy and performance of quantum processors and at the same time remarkably reduce the classical control resources needed, which is a true bottleneck towards scaling up error correction and optimal control methods. In order to ensure usability in the field, we will develop this controller hand in hand among microwave hardware engineers, academic experimental physicists in superconducting circuits, quantum machine learning theorists and a quantum computing startup, which specializes in quantum error corrected qubits. Over the course of the project, we will demonstrate the efficiency of reinforcement learning for model independent optimization of state preparation, stabilization by feedback and quantum error correction.
We plan to deploy this technology within the project duration. This will be done in two different ways that will make it readily available to the entire community. First, a commercial product, a universal quantum controller, will be deployed and will include a user friendly interface and open source code libraries for the implementation of our approach on a variety of quantum processors and devices. Second, by the end of the project, we plan to make an online quantum processor with configurable neural network based feedback available to the public, which would allow researchers, even ones with no quantum hardware, to explore this new approach towards practical quantum computing and quantum sensing.




  • Coordinator: Benjamin Huard (Ecole Normale Supérieure de Lyon, Physics Lab, FR)
  • Raphaël Lescanne (Alice and Bob, FR)
  • Florian Marquardt (Max Planck Institute for the Science of Light, Erlangen, DE)
  • Yonatan Cohen (Quantum Machines, IL)



Call year

Call 2021

Call topic

Applied Quantum Science

Area of research

Quantum computation

Start date

April 2022


36 months

Funding support

€ 902 575

Project status

In Progress