The Machine-Learning toolbox for Quantum Physics
NetKet is an open-source project delivering cutting-edge methods for the study of many-body quantum systems with artificial neural networks and machine learning techniques.
Neural Quantum States
NetKet provides state-of-the-art Neural-Network Quantum states, and advanced learning algorithms to study many-body quantum systems.
Netket is based on Jax, therefore you can run on CPUs, GPUs and TPUs any Neural Network Architecture written in one of the several Jax Frameworks, such as Flax or Haiku.
NetKet can easily interoperate with other tools such as OpenFermion or QuTiP.
NetKet allows you to easily find the ground state or simulate the dynamics of a quantum system.
Easy to use
NetKet has an high-level syntax that is easy to use, while exposing low level objects that can be combined together to develop novel algorithms.
NetKet is a collaborative effort by a group of researchers. We are constantly looking for new contributors. Do get in touch with us through the Github Discussions or through our Slack Channel