A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines.

•Autoencoders are a growing family of tools for nonlinear feature fusion.•A taxonomy of these methods is proposed, detailing each one of them.•Comparisons to other feature fusion techniques and applications are studied.•Guidelines on autoencoder design and example results are provided.•Available software for building autoencoders is summarized.