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/163251/10168612
cpp supported.cpp
#include "nn-utility.h"
using namespace nn_utility;
template T WIDROW_HOFF::WidrowHoff( VECTOR in, VECTOR weight, T bias, int length ){
T result = bias;
for ( int i = 0; i < leng
www.eeworm.com/read/161373/10421303
h bpnet.h
#include "math.h"
#include
#include
#define BP_LEARNING (float)(0.5)//学习系数
class CBPNet
{
public:
CBPNet();
~CBPNet();
float Train(float,float,float);
float Run(float
www.eeworm.com/read/159921/10587889
m contents.m
% Minimax learning algorithm.
%
% mmdemo - Demonstration of the minimax learning algorithm.
% mmln - Minimax learning algorithm for estimation of
% normal distribut
www.eeworm.com/read/421949/10676575
m contents.m
% Minimax learning algorithm.
%
% mmdemo - Demonstration of the minimax learning algorithm.
% mmln - Minimax learning algorithm for estimation of
% normal distribut
www.eeworm.com/read/349415/10828347
cpp supported.cpp
#include "nn-utility.h"
using namespace nn_utility;
template T WIDROW_HOFF::WidrowHoff( VECTOR in, VECTOR weight, T bias, int length ){
T result = bias;
for ( int i = 0; i < leng
www.eeworm.com/read/448038/7541254
m som_settings.m
function settings = som_settings(type)
% default setting structure for Kohonen maps and counterpropagation artificial neural networks (CPANNs)
% som_settings build a default structure with all the
www.eeworm.com/read/325428/13206678
dpr project1.dpr
program Project1;
uses
Forms,
Unit1 in 'Unit1.pas' {Form1};
{$R *.res}
begin
Application.Initialize;
Application.Title := 'Delphi Object-Model and Interface learning';
Applicat
www.eeworm.com/read/140847/5779094
m mixexp2.m
% Fit a piece-wise linear regression model.
% Here is the model
%
% X \
% | |
% Q |
% | /
% Y
%
% where all arcs point down.
% We condition everything on X, so X is a root node. Q is a softmax, a
www.eeworm.com/read/133943/5897280
m mixexp2.m
% Fit a piece-wise linear regression model.
% Here is the model
%
% X \
% | |
% Q |
% | /
% Y
%
% where all arcs point down.
% We condition everything on X, so X is a root node. Q is a softmax, a