Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
Authors: Stephen K. N. Portillo, John K. Parejko, Jorge R. Vergara, and Andrew J. Connolly
2020 The Astronomical Journal16045.
Provider: AAS Journals
Caption: Figure 1.
Structure of an autoencoder with a 4-3-2-3-4 architecture. It compresses four-dimensional inputs to a two-dimensional latent space and both the encoder and decoder are single layers with three neurons.