Detecting stable patterns

John Shawe‐Taylor, Nello CristianiniCambridge 2004 · DOI · OpenAlex

Abstract

As discussed in Chapter 1 perhaps the most important property of a pattern analysis algorithm is that it should identify statistically stable patterns. A stable relation is one that reflects some property of the source generating the data, and is therefore not a chance feature of the particular dataset. Proving that a given pattern is indeed significant is the concern of ‘learning theory’, a body of principles and methods that estimate the reliability of pattern functions under appropriate assumptions about the way in which the data was generated. The most common assumption is that the individual training examples are generated independently according to a fixed distribution, being the same distribution under which the expected value of the pattern function is small. Statistical analysis of the problem can therefore make use of the law of large numbers through the ‘concentration’ of certain random variables.
BibTeX
@inproceedings{shawetaylor2004detecting,
  author = {John Shawe‐Taylor and Nello Cristianini},
  title = {{Detecting stable patterns}},
  booktitle = {Cambridge},
  year = {2004},
  doi = {10.1017/cbo9780511809682.005},
}

Loading related content...

Figure