||It has been suggested that this article be merged with Feature vector. (Discuss) Proposed since March 2013.|
In machine learning and pattern recognition, the term feature space refers to two related, but distinct notions. In basic usage, it refers to an abstract space defined by a feature extraction procedure that transforms raw data into sample vectors of some fixed length.
However, in kernel methods such as the support vector machine, the preceding is actually termed input space, and the term feature space is reserved for the space in which similarity computes are performed implicitly by the kernel function.
See also 
|This computer science article is a stub. You can help Wikipedia by expanding it.|