代码搜索：Learning
找到约 5,352 项符合「Learning」的源代码
代码结果 5,352
www.eeworm.com/read/357874/10199052
m backpropagation_batch.m
function [test_targets, Wh, Wo, J] = Backpropagation_Batch(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm
% Inputs
www.eeworm.com/read/357874/10199069
m backpropagation_quickprop.m
function [test_targets, Wh, Wo, J] = Backpropagation_Quickprop(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm and q
www.eeworm.com/read/357874/10199158
m backpropagation_cgd.m
function [test_targets, Wh, Wo, errors] = Backpropagation_CGD(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm and co
www.eeworm.com/read/357874/10199179
m backpropagation_sm.m
function [test_targets, Wh, Wo, J] = Backpropagation_SM(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with stochastic learning algorithm with mome
www.eeworm.com/read/349842/10796958
m rbf_network.m
function [D, mu, Wo] = RBF_Network(train_features, train_targets, Nh, region)
% Classify using a backpropagation network with a batch learning algorithm
% Inputs:
% features- Train features
% t
www.eeworm.com/read/458224/7301654
linux gpn_ada.m.linux
% Simulate a goal programming network
% Adaptive learning rate strategy has been used
% For details, see
% Van Hulle, M.M. (1991). A Goal Programming Network for Linear
% Programming, Bio. Cybern.,
www.eeworm.com/read/458224/7301661
m gpn_ada.m
% Simulate a goal programming network
% Adaptive learning rate strategy has been used
% For details, see
% Van Hulle, M.M. (1991). A Goal Programming Network for Linear
% Programming, Bio. Cybern.,
www.eeworm.com/read/440433/7689450
m backpropagation_quickprop.m
function [test_targets, Wh, Wo, J] = Backpropagation_Quickprop(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm and q
www.eeworm.com/read/399996/7816591
m backpropagation_batch.m
function [test_targets, Wh, Wo, J] = Backpropagation_Batch(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm
% Inputs
www.eeworm.com/read/399996/7816643
m backpropagation_quickprop.m
function [test_targets, Wh, Wo, J] = Backpropagation_Quickprop(train_patterns, train_targets, test_patterns, params)
% Classify using a backpropagation network with a batch learning algorithm and q