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/407916/11408577
cpp adtreelearner.cpp
/*
* This file is part of MultiBoost, a multi-class
* AdaBoost learner/classifier
*
* Copyright (C) 2005-2006 Norman Casagrande
* For informations write to nova77@gmail.com
*
* This library is
www.eeworm.com/read/407916/11408581
h adtreelearner.h
/*
* This file is part of MultiBoost, a multi-class
* AdaBoost learner/classifier
*
* Copyright (C) 2005-2006 Norman Casagrande
* For informations write to nova77@gmail.com
*
* This library is
www.eeworm.com/read/407916/11408600
h haardata.h
/*
* This file is part of MultiBoost, a multi-class
* AdaBoost learner/classifier
*
* Copyright (C) 2005-2006 Norman Casagrande
* For informations write to nova77@gmail.com
*
* This library is
www.eeworm.com/read/400577/11572562
m spatm.m
%SPATM Augment image dataset with spatial label information
%
% E = SPATM(D,S)
% E = D*SPATM([],S)
%
% INPUT
% D image dataset classified by a classifier
% S smoothing paramet
www.eeworm.com/read/400577/11572628
m averagec.m
%AVERAGEC Combining of linear classifiers by averaging coefficients
%
% W = AVERAGEC(V)
% W = V*AVERAGEC
%
% INPUT
% V A set of affine base classifiers.
%
% OUTPUT
% W Combined classifier.
%
%
www.eeworm.com/read/400577/11572631
m rbnc.m
%RBNC Radial basis function neural network classifier
%
% W = RBNC(A,UNITS)
%
% INPUT
% A Dataset
% UNITS Number of RBF units in hidden layer
%
% OUTPUT
% W Radial basis neural n
www.eeworm.com/read/400577/11573188
m costm.m
%COSTM Cost mapping, classification using costs
%
% Y = COSTM(X,C,LABLIST)
% W = COSTM([],C,LABLIST)
%
% DESCRIPTION
% Maps the classifier output X (assumed to be posterior probability
% estimate
www.eeworm.com/read/342008/12047443
m clevalf.m
%CLEVALF Classifier evaluation (feature size curve)
%
% [e,s] = clevalf(classf,A,featsizes,learnsize,n,T,print)
%
% Generates at random for all feature sizes stored in featsizes
% training sets of
www.eeworm.com/read/342008/12047500
m emclust.m
%EMCLUST Expectation - Maximization clustering
%
% [D,V] = emclust(A,W,n)
%
% The untrained classifier W is used to update an initially labelled
% dataset A by the following two steps:
% 1. train W by
www.eeworm.com/read/255755/12057186
m spatm.m
%SPATM Augment image dataset with spatial label information
%
% E = SPATM(D,S)
% E = D*SPATM([],S)
%
% INPUT
% D image dataset classified by a classifier
% S smoothing parameter