Multiple discriminant analysis
In pattern classification, Multiple Discriminant Analysis (MDA) is a method for compressing a multivariate signal to yield a lower dimensional signal amenable to classification.[1]
MDA is not directly used to perform classification, but rather it yields a compressed signal that is amenable to classification. The method described in Duda et al. (2001) §3.8.3 projects the multivariate signal down to an M−1 dimensional space where M is the number of categories.
MDA is useful because most classifiers are strongly affected by the curse of dimensionality. In other words, when signals are represented in very high dimensional spaces, the classifier's performance is catastrophically impaired by the over-fitting problem. By compressing the signal down to a lower-dimensional space, the problem of over-fitting is reduced.
MDA has been used to reveal the codes contained in neural signals of a very high dimensionality.[2][3]
References
- ^ Duda R, Hart P, Stork D (2001) Pattern Classification, Second Edition. New York, NY, USA: John Wiley and Sons.
- ^ Lin L et. al. (2005) Identification of network-level coding units for real-time representation of episodic experiences in the hippocampus. PNAS 102(17):6125-6130.
- ^ Lin L, Osan R, and Tsien JZ (2006) Organizing principles of real-time memory encoding: neural clique assemblies and universal neural codes. TRENDS in Neurosciences 29(1):48-57.