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

Abstract

Many of the existing machine learning algorithms, both supervised and unsupervised, depend on the quality of the input characteristics to generate a good model. The amount of these variables is also important, since performance tends to decline as the input dimensionality increases, hence the interest in using feature fusion techniques, able to produce feature sets that are more compact and higher level. A plethora of procedures to fuse original variables for producing new ones has been developed in the past decades. The most basic ones use linear combinations of the original variables, such as PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis), while others find manifold embeddings of lower dimensionality based on non-linear combinations, such as Isomap or LLE (Linear Locally Embedding) techniques. More recently, autoencoders (AEs) have emerged as an alternative to manifold learning for conducting nonlinear feature fusion. Dozens of AE models have been proposed lately, each with its own specific traits. Although many of them can be used to generate reduced feature sets through the fusion of the original ones, there also AEs designed with other applications in mind. The goal of this paper is to provide the reader with a broad view of what an AE is, how they are used for feature fusion, a taxonomy gathering a broad range of models, and how they relate to other classical techniques. In addition, a set of didactic guidelines on how to choose the proper AE for a given task is supplied, together with a discussion of the software tools available. Finally, two case studies illustrate the usage of AEs with datasets of handwritten digits and breast cancer.

References in corpus (4)

• Deep Learning in Neural Networks: An Overview
• Knowledge Matters: Importance of Prior Information for Optimization
• Distributed optimization of deeply nested systems
• Autoencoder-based holographic image restoration

Cited by in corpus (13)

• Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
• An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges
• Generative Capacity of Probabilistic Protein Sequence Models
• Tips, guidelines and tools for managing multi-label datasets: the mldr.datasets R package and the Cometa data repository
• Reducing Data Complexity using Autoencoders with Class-informed Loss Functions
• EvoAAA: An evolutionary methodology for automated \neural autoencoder architecture search
• Towards Phytoplankton Parasite Detection Using Autoencoders
• Visual Sensor Network Stimulation Model Identification via Gaussian Mixture Model and Deep Embedded Features
• The Classification of Optical Galaxy Morphology Using Unsupervised Learning Techniques
• A Showcase of the Use of Autoencoders in Feature Learning Applications
• Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion
• Improving Large-Scale k-Nearest Neighbor Text Categorization with Label Autoencoders
• AEGR: A simple approach to gradient reversal in autoencoders for network anomaly detection