@article {295, title = {Ruta: implementations of neural autoencoders in R}, journal = {Knowledge-Based Systems}, volume = {174}, year = {2019}, note = {TIN2015-68854-R,BigDaP-TOOLS}, month = {06/2019}, pages = {4-8}, abstract = {Autoencoders are neural networks which perform feature learning on data. Many variants can be found in the literature, but their implementations are scarce, in separate software pieces and utilizing different languages and frameworks. The ruta package implements a unified foundation for the construction and training of autoencoders on top of Keras and Tensorflow, and allows for easy access to the main functionalities as well as full customization of their diverse aspects.}, doi = {-}, author = {David Charte and F. Herrera and Francisco Charte} }