Methods Based On Proximity Matrices
A method based on proximity matrices is one where the data is presented to the algorithm in the form of a similarity matrix or a distance matrix. These methods all fall under the broader class of metric multidimensional scaling. The variations tend to be differences in how the proximity data is computed; for example, Isomap, locally linear embeddings, maximum variance unfolding, and Sammon mapping (which is not in fact a mapping) are examples of metric multidimensional scaling methods.
Read more about this topic: Nonlinear Dimensionality Reduction
Famous quotes containing the words methods, based and/or proximity:
“Generalization, especially risky generalization, is one of the chief methods by which knowledge proceeds... Safe generalizations are usually rather boring. Delete that “usually rather.” Safe generalizations are quite boring.”
—Joseph Epstein (b. 1937)
“What strikes many twin researchers now is not how much identical twins are alike, but rather how different they are, given the same genetic makeup....Multiples don’t walk around in lockstep, talking in unison, thinking identical thoughts. The bond for normal twins, whether they are identical or fraternal, is based on how they, as individuals who are keenly aware of the differences between them, learn to relate to one another.”
—Pamela Patrick Novotny (20th century)
“Our senses perceive no extreme. Too much sound deafens us; too much light dazzles us; too great distance or proximity hinders our view. Too great length and too great brevity of discourse tends to obscurity; too much truth is paralyzing.... In short, extremes are for us as though they were not, and we are not within their notice. They escape us, or we them.”
—Blaise Pascal (1623–1662)