NetKet Challenges

Call for contributions is open

Get Involved Now


filter_1

Convolutional

Status: Completed

Add complex-valued convolutional neural networks as a built-in Machine.

filter_2

Feed-Forward

Status: Completed

Add complex-valued feed-forward neural networks as a built-in Machine.

filter_3

Deep Boltzmann

Status: Assigned

Add two-layer, complex-valued deep Boltzmann Machines with a few deep units, as a built-in Machine.

filter_4

Supervised Learning

Status: Assigned

Add learning methods to perform supervised learning with the neural-network quantum states in NetKet.

filter_5

Unsupervised Learning

Status: Assigned

Add learning methods to perform unsupervised learning with the neural-network quantum states in NetKet.

filter_6

Exact Diagonalization

Status: Assigned

With a few tweaks, the NetKet infrastructure can be used to perform exact diagonalization on small quantum problems.

filter_7

Built-in Graphs

Status: Assigned

Adding new built-in graphs to NetKet and reduce dependence on external libraries.

filter_8

Optimizers

Status: Completed

Extend the current choice of optimizers, for example taking inspiration from the excellent selection available in TensorFlow.

filter_9_plus

More

Status: Open

Feel free to suggest your own NetKet challenge, the only limit is your imagination (and feasibility!).


Be part of the exciting developments of machine learning for quantum systems, and undertake one of the NetKet challenges.
All contributors will be involved in a collective publication where NetKet will be officially introduced.
Contributions received later than November 2018 might not be considered at this time.