|Title||EvoAAA: An evolutionary methodology for automated neural autoencoder architecture search|
|Publication Type||Journal Article|
|Year of Publication||2020|
|Authors||Charte, Francisco, Rivera-Rivas A.J., Martínez Francisco, and del Jesus M. J.|
|Journal||Integrated Computer-Aided Engineering|
|Keywords||Autoencoder, evolutionary methods, Representation learning|
Machine learning models work better when curated features are provided to them. Feature engineering methods have been usually used as a preprocessing step to obtain or build a proper feature set. In late years, autoencoders (a specific type of symmetrical neural network) have been widely used to perform representation learning, proving their competitiveness against classical feature engineering algorithms. The main obstacle in the use of autoencoders is finding a good architecture, a process that most experts confront manually. An automated autoencoder symmetrical architecture search procedure, based on evolutionary methods, is proposed in this paper. The methodology is tested against nine heterogeneous data sets. The obtained results show the ability of this approach to find better architectures, able to concentrate most of the useful information in a minimized encoding, in a reduced time.
EvoAAA: An evolutionary methodology for automated neural autoencoder architecture search