代码搜索：classifier
找到约 4,824 项符合「classifier」的源代码
代码结果 4,824
www.eeworm.com/read/450608/7480436
m bayesc.m
%BAYESC Bayes classifier
%
% W = BAYESC(WA,WB, ... ,P,LABLIST)
%
% INPUT
% WA, WB, ... Trained mappings for supplying class density estimates
% P Vector with class prior probabili
www.eeworm.com/read/450608/7480455
m getcost.m
%GETCOST Get classification cost matrix
%
% [COST,LABLIST] = GETCOST(W)
%
% Returns the classification cost matrix as set in the classifier W.
% An empty cost matrix is interpreted as equal costs for
www.eeworm.com/read/442927/7641799
m linctrainmre.m
function [recogRate, coef, regError]=lincTrainMre(DS, CParam, plotOpt)
% lincTrainMre: Linear classifier training for min. regression error
% Usage: [recogRate, coef, regError]=lincTrainMre(DS, CPar
www.eeworm.com/read/441245/7673016
m nbayesc.m
%NBAYESC Bayes Classifier for given normal densities
%
% W = NBAYESC(U,G)
%
% INPUT
% U Dataset of means of classes
% G Covariance matrices (optional; default: identity matrices)
%
% OUTP
www.eeworm.com/read/441245/7673220
m neurc.m
%NEURC Automatic neural network classifier
%
% W = NEURC (A,UNITS)
%
% INPUT
% A Dataset
% UNITS Number of units
% Default: 0.2 x size smallest class in A.
%
% OUTPUT
% W T
www.eeworm.com/read/441245/7673222
m testp.m
%TESTP Error estimation of Parzen classifier
%
% E = TESTP(A,H,T)
% E = TESTP(A,H)
%
% INPUT
% A input dataset
% H matrix smoothing parameters (optional, def: determined via
%
www.eeworm.com/read/441245/7673238
m testauc.m
%TESTAUC Multiclass error area under the ROC
%
% E = TESTAUC(A*W)
% E = TESTAUC(A,W)
% E = A*W*TESTAUC
%
% INPUT
% A Dataset to be classified
% W Classifier
%
% OUTPUT
% E Er
www.eeworm.com/read/441245/7673239
m bayesc.m
%BAYESC Bayes classifier
%
% W = BAYESC(WA,WB, ... ,P,LABLIST)
%
% INPUT
% WA, WB, ... Trained mappings for supplying class density estimates
% P Vector with class prior probabili
www.eeworm.com/read/441245/7673268
m getcost.m
%GETCOST Get classification cost matrix
%
% [COST,LABLIST] = GETCOST(W)
%
% Returns the classification cost matrix as set in the classifier W.
% An empty cost matrix is interpreted as equal costs for
www.eeworm.com/read/436945/7758494
m plotdr.m
function plotdr(f, varargin)
%PLOTDR Plot decision regions for classifier object.
% PLOTDR(F, ...) plots the decision boundaries of maximum posterior
% likelihood for different classes where F is