代码搜索：Gradient
找到约 2,951 项符合「Gradient」的源代码
代码结果 2,951
www.eeworm.com/read/212217/4938403
cpp gradientdoc.cpp
// gradientDoc.cpp : CgradientDoc 类的实现
//
#include "stdafx.h"
#include "gradient.h"
#include "gradientDoc.h"
#ifdef _DEBUG
#define new DEBUG_NEW
#endif
// CgradientDoc
IMPLEMENT_
www.eeworm.com/read/212217/4938405
cpp gradientview.cpp
// gradientView.cpp : CgradientView 类的实现
//
#include "stdafx.h"
#include "gradient.h"
#include "gradientDoc.h"
#include "gradientView.h"
#include ".\gradientview.h"
#ifdef _DEBUG
#define
www.eeworm.com/read/212217/4938595
cpp gradientdoc.cpp
// gradientDoc.cpp : CgradientDoc 类的实现
//
#include "stdafx.h"
#include "gradient.h"
#include "gradientDoc.h"
#ifdef _DEBUG
#define new DEBUG_NEW
#endif
// CgradientDoc
IMPLEMENT_
www.eeworm.com/read/344585/3207706
m mlpbkp.m
function g = mlpbkp(net, x, z, deltas)
%MLPBKP Backpropagate gradient of error function for 2-layer network.
%
% Description
% G = MLPBKP(NET, X, Z, DELTAS) takes a network data structure NET
% togeth
www.eeworm.com/read/344585/3207810
m mlpgrad.m
function [g, gdata, gprior] = mlpgrad(net, x, t)
%MLPGRAD Evaluate gradient of error function for 2-layer network.
%
% Description
% G = MLPGRAD(NET, X, T) takes a network data structure NET together
www.eeworm.com/read/325480/3483481
m optimize.m
function [co, p, fret, its]=optimize(co, p, param)
% [co, p, fret, iter]=cg_optimizable.optimize(co, p)
%
% The Fletcher-Reeves-Polak-Ribiere-Conjugate Gradient Algorithm
% (from Numerical Recipe
www.eeworm.com/read/299717/3851109
m optimize.m
function [co, p, fret, its]=optimize(co, p, param)
% [co, p, fret, iter]=cg_optimizable.optimize(co, p)
%
% The Fletcher-Reeves-Polak-Ribiere-Conjugate Gradient Algorithm
% (from Numerical Recipe
www.eeworm.com/read/396844/2406637
m mlpbkp.m
function g = mlpbkp(net, x, z, deltas)
%MLPBKP Backpropagate gradient of error function for 2-layer network.
%
% Description
% G = MLPBKP(NET, X, Z, DELTAS) takes a network data structure NET
% togeth
www.eeworm.com/read/396844/2406742
m mlpgrad.m
function [g, gdata, gprior] = mlpgrad(net, x, t)
%MLPGRAD Evaluate gradient of error function for 2-layer network.
%
% Description
% G = MLPGRAD(NET, X, T) takes a network data structure NET together
www.eeworm.com/read/359369/2978436
m mlpbkp.m
function g = mlpbkp(net, x, z, deltas)
%MLPBKP Backpropagate gradient of error function for 2-layer network.
%
% Description
% G = MLPBKP(NET, X, Z, DELTAS) takes a network data structure NET
% t