Feature Selection Techniques in High Dimensional Data With Machine Learning and Deep Learning

Abstract

High-dimensional data inspection is one of the major disputes for researchers plus engineers in domains of deep learning (DL), machine learning (ML), as well as data mining. Feature selection (FS) endows with proficient manner to determine these difficulties through eradicating unrelated and outdated data, which be capable of reducing calculation time, progress learns precision, and smooth the progress of an enhanced understanding of the learning representation or information. To eradicate an inappropriate feature, an FS standard was essential, which can determine the significance of every feature in the company of the output class/labels. Filter schemes employ variable status procedure as the standard criterion for variable collection by means of ordering. Ranking schemes utilized since their straightforwardness and high-quality accomplishment are detailed for handy appliances. The goal of this chapter is to produce complete information on FS approaches, its applications, and future research directions.