TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
TetrisCNN is introduced, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators, and opens the way to integrating interpretable neural networks with quantum simulators...
Kacper Cybiński, B. V. Van Zwol, James Enouen et al.
· 0 citations