Hybrid GP/PSO Representation of 1-D Signals in an Autoencoder Fashion

Giulia Magnani, Monica Mordonini, Stefano Cagnoni

Abstract: A popular low-dimensional latent representation that retains as much information as possible about a data set is the one represented by the output of a hidden layer located within a neural net having homomorphic input and output layers, termed autoencoder, trained to produce a copy of the input data as its output.

External IDs:doi:10.1007/978-3-031-57430-6_18