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/344585/3207672
m netgrad.m
function g = netgrad(w, net, x, t)
%NETGRAD Evaluate network error gradient for generic optimizers
%
% Description
%
% G = NETGRAD(W, NET, X, T) takes a weight vector W and a network data
% structure
www.eeworm.com/read/344585/3207723
m scg.m
function [x, options, flog, pointlog, scalelog] = scg(f, x, options, gradf, varargin)
%SCG Scaled conjugate gradient optimization.
%
% Description
% [X, OPTIONS] = SCG(F, X, OPTIONS, GRADF) uses a sca
www.eeworm.com/read/344585/3207738
m olgd.m
function [net, options, errlog, pointlog] = olgd(net, options, x, t)
%OLGD On-line gradient descent optimization.
%
% Description
% [NET, OPTIONS, ERRLOG, POINTLOG] = OLGD(NET, OPTIONS, X, T) uses on
www.eeworm.com/read/344585/3207757
m gpgrad.m
function g = gpgrad(net, x, t)
%GPGRAD Evaluate error gradient for Gaussian Process.
%
% Description
% G = GPGRAD(NET, X, T) takes a Gaussian Process data structure NET
% together with a matrix X of
www.eeworm.com/read/344585/3207771
m glmgrad.m
function [g, gdata, gprior] = glmgrad(net, x, t)
%GLMGRAD Evaluate gradient of error function for generalized linear model.
%
% Description
% G = GLMGRAD(NET, X, T) takes a generalized linear model da
www.eeworm.com/read/344585/3207974
m hill_obj.m
function [f,df]=hill_obj(x,dims,ii,dd,pars);
%
% computes the objective function and gradient of the non-convex formulation of MVU.
%
% copyright by Kilian Q. Weinberger, 2006
%
%
%
% This file is
www.eeworm.com/read/304358/3799782
m definev.m
function [v,dv]= definev(g,x,l,u);
%DEFINEV Scaling vector and derivative
%
% [v,dv]= DEFINEV(g,x,l,u) returns v, distances to the
% bounds corresponding to the sign of the gradient g, where
%
www.eeworm.com/read/296073/3908127
cfg theme.cfg
# blueflux
# theme for fluxbox
# 2003 (c) BioNiK
# edited from skypher's theme, thanks fluxgen for the awesome work with fluxbox ;)
toolbar: flat gradient vertical
toolbar.color: #527d8b
www.eeworm.com/read/292984/3935743
m mixexp_graddesc.m
%%%%%%%%%%
function [theta, eta] = mixture_of_experts(q, data, num_iter, theta, eta)
% MIXTURE_OF_EXPERTS Fit a piecewise linear regression model using stochastic gradient descent.
% [theta, eta] =
www.eeworm.com/read/292984/3936122
m maximize_params.m
function CPD = maximize_params(CPD, temp)
% MAXIMIZE_PARAMS Find ML params of an MLP using Scaled Conjugated Gradient (SCG)
% CPD = maximize_params(CPD, temperature)
% temperature parameter is igno