Open Access

Fig. 1

image

Download original image

Disentanglement architecture featuring multi-discriminators. The architecture operates as follows: spectra x and stellar parameters y are concatenated as input. The encoder then maps this concatenated input, xy, to the latent space z, with the aim of disentangling y from z. Subsequently, the decoder’s task is to reconstruct x using zy as input. In parallel, discriminators receive z as input and endeavour to predict the astrophysical parameters within a discretised space yd.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.