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/361257/10062744
m nnd12cg.m
function nnd12cg(cmd,arg1)
%NND12CG Conjugate gradient backpropagation demonstration.
%
% This demonstration requires the Neural Network Toolbox.
% First Version, 8-31-95.
%==================
www.eeworm.com/read/161189/10440092
m bfgs.m
%
% xstar=bfgs(func,delf,x0,tol,maxiter)
%
% Use steepest descent to minimize a function f(x).
%
% func name of the function f(x)
% delf name of the gradient del f(x)
% x0
www.eeworm.com/read/351010/10688422
m nnd12cg.m
function nnd12cg(cmd,arg1)
%NND12CG Conjugate gradient backpropagation demonstration.
%
% This demonstration requires the Neural Network Toolbox.
% First Version, 8-31-95.
%==================
www.eeworm.com/read/158963/10707516
m nnd12cg.m
function nnd12cg(cmd,arg1)
%NND12CG Conjugate gradient backpropagation demonstration.
%
% This demonstration requires the Neural Network Toolbox.
% First Version, 8-31-95.
%==================
www.eeworm.com/read/274975/10841965
m nnd12cg.m
function nnd12cg(cmd,arg1)
%NND12CG Conjugate gradient backpropagation demonstration.
%
% This demonstration requires the Neural Network Toolbox.
% First Version, 8-31-95.
%==================
www.eeworm.com/read/448535/7531583
m conjgradtest.m
% Test the conjugate gradient algorithm
% Copyright 1999 by Todd K. Moon
hold off
; rosenbrock;
hold on
xoff = -.3;
x = [-1;-1];
[xn,X] = conjgrad2(x,'rosengrad','rosenhess')
[n,k] = size
www.eeworm.com/read/447486/7550068
m definemodel.m
function [model] = defineModel(dx,dy,model,quantVal)
%Build a 2D Gradient histogram
%Scale image between 0 and 255
sgradX = scale(dx,[0 255]);
sgradY = scale(dy,[0 255]);
%Quantize image
www.eeworm.com/read/434325/7874550
m grads.m
function [P0,y0,h,err,P,Y] = grads(Fn,Gn,P0,max1,delta,epsilon,show)
%---------------------------------------------------------------------------
%GRADS Gradient search for a minimum.
% Sample ca
www.eeworm.com/read/298871/7928892
m nnd12cg.m
function nnd12cg(cmd,arg1)
%NND12CG Conjugate gradient backpropagation demonstration.
%
% This demonstration requires the Neural Network Toolbox.
% First Version, 8-31-95.
%==================
www.eeworm.com/read/396828/8088287
m traincgp_snn.m
function [net, result] = traincgp_snn(net, dataLV, dataVV, dataTV)
%TRAINCGP_SNN Conjugate gradient training (Polak - Ribiere).
%
% Syntax
%
% [net, tr_info] = traincgp_snn(net, dataLV)
% [net, t