1 | % DisTools Table of Contents
|
---|
2 | % 23-Nov-2009_17:27
|
---|
3 | %
|
---|
4 | % This Matlab toolbox for the analysis of dissimilarity data works only
|
---|
5 | % if also the pattern recognition toolbox PRTools is available.
|
---|
6 | % See http://prtools.org
|
---|
7 | %
|
---|
8 | % E. Pekalska, ela.pekalska@googlemail.com, University of Manchester
|
---|
9 | % R.P.W. Duin, r.duin@ieee.org, Delft University of Technology
|
---|
10 | %
|
---|
11 | % Characterization of dissimilarity matrices
|
---|
12 | % ------------------------------------------
|
---|
13 | % CHECKEUCL Check whether a square dissimilarity matrix has a Euclidean behavior
|
---|
14 | % CHECKTR Check whether a square dissimilarity matrix obeys triangle inequality
|
---|
15 | % CHARDMAT Fiand several characteristic of (dis)similarity data
|
---|
16 | % CORRTR Correct a square dissimilarity matrix to obey the triangle inequality
|
---|
17 | % DISCHECK Dissimilarity matrix check
|
---|
18 | % DISNORM Normalization of a dissimilarity matrix
|
---|
19 | % DISSTAT Basic statistics of the dissimilarity matrix
|
---|
20 | % ISSQUARE Check whether a matrix is square
|
---|
21 | % ISSYM Check whether a matrix is symmetric
|
---|
22 | % ASYMMETRY Compute asymmetry of dissimilarity matrix
|
---|
23 | % NNE Leave-one-out Nearest Neighbor error on a dissimilarity matrix
|
---|
24 | % NNERR Exact expected NN error from a dissimilarity matrix
|
---|
25 | %
|
---|
26 | % Dissimilarity Measures
|
---|
27 | % -----------------------------------------------
|
---|
28 | % COSDISTM Distance matrix based on inner products
|
---|
29 | % EUDISTM Euclidean distance matrix
|
---|
30 | % HAMDISTM Hamming distance matrix between binary vectors
|
---|
31 | % HAUSDM Hausdorff and modified Hausdorff distance between datasets of image blobs
|
---|
32 | %
|
---|
33 | % Transformations
|
---|
34 | % DISSIMT Fixed DISsimilarity-SIMilarity transformation
|
---|
35 | % MAKESYM Make a matrix symmetric
|
---|
36 | % PE_EM Pseudo-Euclidean embedding (includes Classical Scaling as a special case)
|
---|
37 | %
|
---|
38 | % Classification in Pseudo-Euclidean Space and indefinite kernels
|
---|
39 | % -----------------------------------------------
|
---|
40 | % SETSIG Set PE signature for mappings or datasets
|
---|
41 | % GETSIG Set PE signature for mappings or datasets
|
---|
42 | % ISPE_DATASET Test dataset for PE signature setting
|
---|
43 | % ISPE_EM Test mapping for PE signature setting
|
---|
44 | % PE_DISTM Square pseudo-Euclidean distance between two datasets
|
---|
45 | % PE_KERNELM Compute kernel in PE space
|
---|
46 | % PE_MTIMES Matrix multiplication (inner product) in PE space
|
---|
47 | % PE_PARZENC Parzen classifier in PE space
|
---|
48 | % PE_KNNC KNN classifier in PE space
|
---|
49 | % PE_NMC Nearest mean classifier in PE space
|
---|
50 | % PE_EM Pseudo-Euclidean linear embedding
|
---|
51 | % PLOTSPECTRUM Plot spectrum of eigenvalues
|
---|
52 | %
|
---|
53 | % Routines supporting in learning from dissimilarity matrices
|
---|
54 | % -----------------------------------------------------------------------
|
---|
55 | % CROSSVALD Cross-validation error for dissimilarity data
|
---|
56 | % CLEVALD Classifier evaluation (learning curve) for dissimilarity data
|
---|
57 | % DISSPACES Compute various spaces out of a dissimilarity matrix
|
---|
58 | % GENDDAT Generate random training and test sets for dissimilarity data
|
---|
59 | % GENREP Generate a representation set
|
---|
60 | % GENREPI Generate indices for representation, learning and testing sets
|
---|
61 | % SELCDAT Select Class Subset from a Square Dissimilarity Dataset
|
---|
62 | % PROTSELFD Forward prototype selection
|
---|
63 | % DLPC LP-classifier on dissimilarity (proximity) data
|
---|
64 | % KNNDC K-Nearest Neighbor classifier for dissimilarity matrices
|
---|
65 | % PARZENDDC Parzen classifier for dissimilarity matrices
|
---|
66 | % TESTKD Test k-NN classifier for dissimilarity data
|
---|
67 | % TESTPD Test Parzen classifier for dissimilarity data
|
---|
68 | %
|
---|
69 | % EXAMPLES
|
---|
70 | % --------
|
---|
71 | % CROSSVALD_EX Crossvalidation of several classifiers
|
---|