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/117227/6105480
java kunststoffgradienttheme.java
package com.incors.plaf.kunststoff;
import javax.swing.plaf.*;
import com.incors.plaf.*;
public class KunststoffGradientTheme implements GradientTheme {
// gradient colors
private final Color
www.eeworm.com/read/415194/6281715
m nonlin_gg.m
function [s, err_cost, iter_time]=nonlin_gg(x,F,C,m,varargin)
% nonlin_gg: Nonlinear sparse approximation by greedy gradient search.
%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
www.eeworm.com/read/415194/6281726
m greed_gp.m
function [s, err_mse, iter_time]=greed_gp(x,A,m,varargin)
% greed_gp: Gradient Pursuit algorithm from [1]
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Usage
% [s, err_
www.eeworm.com/read/415194/6281731
m .15636-199119694-9.m
function [s, err_mse, iter_time]=greed_nomp(x,A,m,varargin)
% greed_nomp: Nearly Orthogonal Matching Pursuit or Approximate Conjugate
% Gradient Pursuit algorithm
%%%%%%%%%%%%%%%%%%%%%%%%
www.eeworm.com/read/415194/6281732
m greed_nomp.m
function [s, err_mse, iter_time]=greed_nomp(x,A,m,varargin)
% greed_nomp: Nearly Orthogonal Matching Pursuit or Approximate Conjugate
% Gradient Pursuit algorithm
%%%%%%%%%%%%%%%%%%%%%%%%
www.eeworm.com/read/489598/6466414
m predict_grad.m
function [xP] = predict_grad(xP,G,rx,lamda)
%This rouine uses the gradient descent algorithm to try to help
%'push' particles to a region of higher probability before the
%state update equation
g
www.eeworm.com/read/485544/6552649
m demolgd1.m
%DEMOLGD1 Demonstrate simple MLP optimisation with on-line gradient descent
%
% Description
% The problem consists of one input variable X and one target variable
% T with data generated by sampling X
www.eeworm.com/read/343492/11944458
m compute_empgrad.m
function v = compute_empgrad(fun,x,fx,scaling,empgradtype,varargin);
% COMPUTE_EMPGRAD - computes the empirical gradient
% empgradtype : 1 - d function evaulations
% 2 - 2*d fu
www.eeworm.com/read/253950/12173322
m demolgd1.m
%DEMOLGD1 Demonstrate simple MLP optimisation with on-line gradient descent
%
% Description
% The problem consists of one input variable X and one target variable
% T with data generated by sampling X
www.eeworm.com/read/339665/12211206
m demolgd1.m
%DEMOLGD1 Demonstrate simple MLP optimisation with on-line gradient descent
%
% Description
% The problem consists of one input variable X and one target variable
% T with data generated by sampling X