β-Variational autoencoder as an entanglement classifier

Highlights: • Using our methods we can encode the information of the entanglement of the quantum state into a latent space. • We can distinguish between entangled and separable states with high precision using both the model and the latent space. • We can distinguish between a set of local measurements and correlated measurements using the latent space. We focus on using an architecture similar to the β-Variational Autoencoder (β-VAE) to discriminate if a quantum state is entangled or separable based on measurements. We split the data into two sets, the set of local and correlated measurements. Using the latent space, which is a low dimensional representation of the data, we show that restricting ourselves to the set of local data it is not possible to distinguish between entangled and separable states. Meanwhile, when considering both correlated and local measurements, an accuracy of over 80% is attained in the structure of the latent space.