- author = "Giulia Magnani and Monica Mordonini and Stefano Cagnoni",
- title = "Hybrid {GP/PSO} Representation of {1-D} Signals in an Autoencoder Fashion",
- booktitle = "17th Italian Workshop on Artificial Life and Evolutionary Computation",
- year = "2023",
- editor = "Marco Villani and Stefano Cagnoni and Roberto Serra",
- volume = "1977",
- series = "Communications in Computer and Information Science",
- pages = "228--238",
- address = "Venice, Italy",
- month = sep # " 6-8",
- publisher = "Springer Nature",
- note = "revised selected papers",
- keywords = "genetic algorithms, genetic programming",
- isbn13 = "978-3-031-57430-6",
-
DOI = "
doi:10.1007/978-3-031-57430-6_18",
-
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.
This exploratory paper suggests that reformulating the problem as a GP-based symbolic regression can achieve the same goal. The latent representation, in this case, is obtained as a byproduct of the solution to the problem of finding a parametric equation that represents a model of a family of signals (functions) that share the same equation, differing only for the values of a set of free parameters that appear in their definition.
This hypothesis is supported by a simple proof of concept based on the results of symbolic regression of a set of Gaussian functions. A discussion of possible issues that might need to be tackled when the method is applied to more complex real-world data and of the corresponding possible countermeasures concludes the paper.",
-
notes = "Also known as
\cite{DBLP:conf/wivace/MagnaniMC23}
Proceedings published after the workshop in 2024 as 'Artificial Life and Evolutionary Computation'",
