代码搜索：NetWork
找到约 10,000 项符合「NetWork」的源代码
代码结果 10,000
www.eeworm.com/read/493401/6402382
makefile
# NOTE: this is a GNU Makefile. You must use "gmake" rather than "make".
#
# Makefile for the network assignment
# Defines set up assuming this assignment is done last
# If not, use the "bare
www.eeworm.com/read/492695/6419438
m example33_test.m
%test the bp network
%==============
%==============
input=str2num(input);
output=purelin(W2*tansig(W1*input,B1),B2);
out=purelin(W2*tansig(W1*P,B1),B2);
figure('color',[0.8 0.8 0.8],'positi
www.eeworm.com/read/492695/6419444
m example32_test.m
%test the rbf network
%==============
%==============
clc;
input=[0 0 1 1;0 1 0 1]
A=simurb(input,W1,B1,W2,B2);
output=round(A)
% set(output,'string',A);
www.eeworm.com/read/492695/6419458
m example34_test.m
%test the rbf network
%==============
%==============
input=str2num(input);
output=simurb(input,W1,B1,W2,B2);
out=simurb(P,W1,B1,W2,B2);
figure('color',[0.8 0.8 0.8],'position',[120 120 600
www.eeworm.com/read/492695/6419478
m example52_figure.m
%hf2_figure
%==============
%==============
%to see the input/output
figure('name','欲记忆矢量','numbertitle','off');
clc
T=[+1 -1;
-1 +1];
plot(T(1,:),T(2,:),'r*')
axis([-2 2 -2 2])
alabel('a
www.eeworm.com/read/492695/6419501
m example35re.m
%nn1R, Recognition of BP network
%===============
%例3.5 训练好的BP网络识别加了噪声的测试样本
%===============
clc;
[length,width]=size(b1);
b=double(b1);
q=reshape(b,length*width,1); %改32*32的矩阵为1024*1的矩阵
www.eeworm.com/read/492400/6422321
m mytrainlm.m
function [net,tr,v3,v4,v5,v6,v7,v8] = ...
trainlm(net,Pd,Tl,Ai,Q,TS,VV,TV,v9,v10,v11,v12)
%TRAINLM Levenberg-Marquardt backpropagation.
%
% Syntax
%
% [net,tr] = trainlm(net,Pd,Tl,Ai,Q,TS,VV)
%
www.eeworm.com/read/491824/6426935
m nnfexist.m
function ok = nnfexist(d)
%NNFEXIST Neural Network Design utility function.
% Copyright 1994-2002 PWS Publishing Company and The MathWorks, Inc.
% $Revision: 1.6 $
% First Version, 8-31-95.
www.eeworm.com/read/490202/6460611
m char3.m
%% Character Recognition Example (III):Training a Simple NN for
%% classification
%% Read the image
I = imread('sample.bmp');
%% Image Preprocessing
img = edu_imgpreprocess(I);
for cnt = 1:5