A Review on Dimensionality Reduction for Machine Learning

In recent years growing volumes of data have made the task of applying various machine learning algorithms a challenge in a great number of cases. This challenge is posed in two main ways: training time and processing load. Normally, problems in these two categories may be attributed to irrelevant, redundant, or noisy features. So as to avoid this type of feature most pre-processing pipelines include a step dedicated so selecting the most relevant features or combining existing ones into a single better representation. These techniques are denominated dimensionality reduction techniques. In this work, we aim to present a short look at the current state of the art in this area.