neural network input .

1 次查看（过去 30 天）
Mo al
Mo al 2011-12-13
i have these code with these input to my neural network , my question is how does the NN take the input ? to be more clear is NN going to take p1[1,1], p2[1,1],p3[1,1].....p13[1,1]; or it will take the whole p1 and after that the whole p2 , p3 ...,p13?
my code is
clear;
clc;
load asp65 ;
load curv65;
load dfd65;
load dffl65;
load dfr65;
load gl65;
load lc65;
load prc65;
load plc65;
load pfc65;
load slop65;
load sot65;
load vec65;
load ele65;
load hlo65;
p1=transpose(asp65);
p2=transpose(curv65);
p3=transpose(dfd65);
p4=transpose(dffl65);
p5=transpose(dfr65);
p6=transpose(gl65);
p7=transpose(lc65);
p8=transpose(prc65);
p9=transpose(plc65);
p10=transpose(pfc65);
p11=transpose(slop65);
p12=transpose(vec65);
p13=transpose(ele65);
t1=transpose(hlo65);
p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13];
%p=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11,p12,p13]
%p15=[p7;p8;p9;p10;p11;12;13];
t=[t1];
%p = [-1 -1 2 2 ;0 5 0 5 ]
%t = [-1 -1 1 1 ];
for i=1:1:10
net=newff(minmax(p),t,[15 , 4],{'tansig','purelin'},'trainrp');
net.performFcn='msereg';
net.performParam.ratio=0.5;
net.trainParam.show = 5;
net.trainParam.lr = 0.5; % learning rate
net.trainParam.epochs = 1000;
net.trainParam.goal = 1e-5;
RandStream.setDefaultStream(RandStream('mt19937ar','seed',1));
%rand('state',sum(100*clock)) % initialize therandom
net = init(net);
[net,tr]=train(net,p,t);
a = sim(net,p);
e = a-t;
rmse = sqrt(mse(e));
acc=1-rmse
%simpleclusterOutputs = sim(net,p);
%plotroc(t,simpleclusterOutputs);
end

请先登录，再回答此问题。

采纳的回答

Mo al
Mo al 2011-12-14
helpppppppppppppppppppppppppppp, any help i have these code with these input to my neural network , my question is how does the NN take the input ? to be more clear is NN going to take p1[1,1], p2[1,1],p3[1,1].....p13[1,1]; or it will take the whole p1 and after that the whole p2 , p3 ...,p13? my code is clear; clc; load asp65 ; load curv65; load dfd65; load dffl65; load dfr65; load gl65; load lc65; load prc65; load plc65; load pfc65; load slop65; load sot65; load vec65; load ele65; load hlo65;
p1=transpose(asp65); p2=transpose(curv65); p3=transpose(dfd65); p4=transpose(dffl65); p5=transpose(dfr65); p6=transpose(gl65); p7=transpose(lc65); p8=transpose(prc65); p9=transpose(plc65); p10=transpose(pfc65); p11=transpose(slop65); p12=transpose(vec65); p13=transpose(ele65); t1=transpose(hlo65);
p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13]; %p=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11,p12,p13] %p15=[p7;p8;p9;p10;p11;12;13]; t=[t1]; %p = [-1 -1 2 2 ;0 5 0 5 ] %t = [-1 -1 1 1 ]; for i=1:1:10 net=newff(minmax(p),t,[15 , 4],{'tansig','purelin'},'trainrp'); net.performFcn='msereg'; net.performParam.ratio=0.5;
net.trainParam.show = 5; net.trainParam.lr = 0.5; % learning rate net.trainParam.epochs = 1000; net.trainParam.goal = 1e-5; RandStream.setDefaultStream(RandStream('mt19937ar','seed',1)); %rand('state',sum(100*clock)) % initialize therandom net = init(net); [net,tr]=train(net,p,t); a = sim(net,p);
e = a-t;
rmse = sqrt(mse(e));
acc=1-rmse
%simpleclusterOutputs = sim(net,p);
%plotroc(t,simpleclusterOutputs);
end
any one can help?????????????????????

更多回答（7 个）

Greg Heath
Greg Heath 2011-12-14
See comments, examples and sample code by searching tne newsgroup using
heath newff close clear
heath newff Neq Nw Ntrials
Hope this helps.
Greg
  1 个评论
Mo al
Mo al 2011-12-15
thank you sir , but couldn't find my answer any way thank you

请先登录，再进行评论。

Mo al
Mo al 2011-12-15
helpppppppppppppppppppppppppppp, any help i have these code with these input to my neural network , my question is how does the NN take the input ? to be more clear is NN going to take p1[1,1], p2[1,1],p3[1,1].....p13[1,1]; or it will take the whole p1 and after that the whole p2 , p3 ...,p13? my code is clear; clc; load asp65 ; load curv65; load dfd65; load dffl65; load dfr65; load gl65; load lc65; load prc65; load plc65; load pfc65; load slop65; load sot65; load vec65; load ele65; load hlo65;
p1=transpose(asp65); p2=transpose(curv65); p3=transpose(dfd65); p4=transpose(dffl65); p5=transpose(dfr65); p6=transpose(gl65); p7=transpose(lc65); p8=transpose(prc65); p9=transpose(plc65); p10=transpose(pfc65); p11=transpose(slop65); p12=transpose(vec65); p13=transpose(ele65); t1=transpose(hlo65);
p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13]; %p=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11,p12,p13] %p15=[p7;p8;p9;p10;p11;12;13]; t=[t1]; %p = [-1 -1 2 2 ;0 5 0 5 ] %t = [-1 -1 1 1 ]; for i=1:1:10 net=newff(minmax(p),t,[15 , 4],{'tansig','purelin'},'trainrp'); net.performFcn='msereg'; net.performParam.ratio=0.5;
net.trainParam.show = 5; net.trainParam.lr = 0.5; % learning rate net.trainParam.epochs = 1000; net.trainParam.goal = 1e-5; RandStream.setDefaultStream(RandStream('mt19937ar','seed',1)); %rand('state',sum(100*clock)) % initialize therandom net = init(net); [net,tr]=train(net,p,t); a = sim(net,p);
e = a-t;
rmse = sqrt(mse(e));
acc=1-rmse
%simpleclusterOutputs = sim(net,p);
%plotroc(t,simpleclusterOutputs);
end
any one can help?????????????????????
Greg Heath
Greg Heath 2011-12-15
>i have these code with these input to my neural network , my question is how does the
>NN take the input ? to be more clear is NN going to take p1[1,1], p2[1,1],p3[1,1].....
>p13[1,1]; or it will take the whole p1 and after that the whole p2 , p3 ...,p13?
It is hard to answer your question without knowing the sizes of the pi (i=1:13).
For an I-H-O node topology and Ntrn I/O training pairs,
[I Ntrn] = size(p)
[O Ntrn] = size(t)
The I/O vectors are columns of p and t.
>my code is clear; clc; load asp65 ; load curv65; load dfd65; load dffl65; load dfr65; >load gl65; load lc65; load prc65; load plc65; load pfc65; load slop65; load sot65; >load vec65; load ele65; load hlo65;
>p1=transpose(asp65); p2=transpose(curv65); p3=transpose(dfd65); p4=transpose(dffl65); >p5=transpose(dfr65); p6=transpose(gl65); p7=transpose(lc65); p8=transpose(prc65); >p9=transpose(plc65); p10=transpose(pfc65); p11=transpose(slop65); p12=transpose(vec65); > p13=transpose(ele65); t1=transpose(hlo65);
>>p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13]; %p=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11,p12,p13] >%p15=[p7;p8;p9;p10;p11;12;13]; t=[t1]; %p = [-1 -1 2 2 ;0 5 0 5 ] %t = [-1 -1 1 1 ];
Size(p)? size(t1)?
Normalization of p and t1?
H = 15, O = 4?
Why 15? Better to search for the smallest good value satisfying
H <= floor( (Ntrn*O-O)/(I+O+1) )
Add an outer loop over candidate H values.
> RandStream.setDefaultStream(RandStream('mt19937ar','seed',1));
Only initialize once BEFORE the loops!
%rand('state',sum(100*clock)) % initialize the random net = init(net);
If you ever do this, replace 100 by 1e9. Don't need INIT because NEWFF is self-initializing.
>for i=1:1:10
>>net=newff(minmax(p),t,[H , O],{'tansig','purelin'},'trainrp');
>net.performFcn='msereg'; net.performParam.ratio=0.5;
Why MSEREG?? Why not use as many defaults as possible?
>net.trainParam.show = 5;
>net.trainParam.lr = 0.5; % learning rate
>net.trainParam.epochs = 1000;
>net.trainParam.goal = 1e-5;
Why 1e-5??
>[net,tr]=train(net,p,t); > a = sim(net,p); e = a-t;
Why not [net, tr, a, e] = ... ?
>rmse = sqrt(mse(e)); >acc=1-rmse
Useless performance index. Use R^2.
Hope this helps.
Greg
%simpleclusterOutputs = sim(net,p);
%plotroc(t,simpleclusterOutputs);
end
Mo al
Mo al 2011-12-16
Greg , thank you very much , about your wondering
1-i have these code with these input to my neural network , my question is how does the
>NN take the input ? to be more clear is NN going to take p1[1,1], p2[1,1],p3[1,1].....
>p13[1,1]; or it will take the whole p1 and after that the whole p2 , p3 ...,p13?
It is hard to answer your question without knowing the sizes of the pi (i=1:13). the p1, p2 ...p12 and p13 each one has 255 by 255 the total p=[ p1; p2; ...;p12 and p13] contain all of them my question is how does the NN will take the all p1which 255 by 255 and after that p2 , p3... p13 or the NN will take the first element in p1 and the first one in p2..... p13 (one by one) ? .==================================================== 2- >>p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13]; %p=[p1,p2,p3,p4,p5,p6,p7,p8,p9,p10,p11,p12,p13] >%p15=[p7;p8;p9;p10;p11;12;13]; t=[t1]; %p = [-1 -1 2 2 ;0 5 0 5 ] %t = [-1 -1 1 1 ];
Size(p)? size(t1)? the size of p is (13 x255)=3315 elements.
the size of (t1) is 255
Normalization of p and t1? all the elements value for (p and t1) between 0 and 1.
H = 15, O = 4? one hidden lair has 15 neuron based on previous researches . out put in the target has two values either 1 or 0 so once i put the output 4 i achieved much better regression and accuracy values . ================================================================== 3-net.performFcn='msereg'; net.performParam.ratio=0.5;
Why MSEREG?? Why not use as many defaults as possible? if i keep the default my accuracy and regression will R=0.333 and the accuracy 90 but if i use net.performFcn='msereg' the R =.6999 and the accuracy 96% =================================== 4-net.trainParam.goal = 1e-5;
Why 1e-5?? its the best value i can get better performance result through . ====================================================== 5->[net,tr]=train(net,p,t); > a = sim(net,p); e = a-t;
Why not [net, tr, a, e] = ... ? what is the wrong with my code why yours is better ? =================================================== 6->rmse = sqrt(mse(e)); >acc=1-rmse
Useless performance index. Use R^2 what is R^2? ============================ thank you in advance
Greg Heath
Greg Heath 2011-12-19
>1-i have these code with these input to my neural network , my question is how does the NN take the input ?
Once the matrix p is created, the net takes the first column of p, then the second column of p, etc. If
[ I N ] = size(p),
then p is interpreted as containing N I-dimensional column vectors. Since
size(pi) = [ 255 255] % i = 1:13
you need to columnize your pi matrices and form
p = [ p1(:), p2(:), ..., p13(:)];
THEN
size(p) = [ 255^2 13] = [ 65025 133 ]
AND
you need to investigate 2-D dimensionality reduction via averaging pixels.
====================================================
>2. p=[p1;p2;p3;p4;p5;p6;p7;p8;p9;p10;p11;p12;p13];
Incorrect. See above
Size(p)? size(t1)?
> the size of p is (13 x255)=3315 elements.
Incorrect. See above.
>the size of (t1) is 255
Incorrect. Size has two dimensions. See the documentation
help size
doc size
The correct answer is
size(t1) = [ O N ]
and is interpreted as N O-dimensional output column vectors.
H = 15, O = 4?
>one hidden lair (sp: layer) has 15 neuron based on previous researches . out put in the target has two values either 1 or 0 so once i put the output 4 i achieved much better regression and accuracy values .
I don't understand. What do the 4 outputs represent?
Oh! Oh! Is this classification and you are using a binary coded output?
For classification use
size(t1) = [ 13 N]
where each column is a column of the 13 dimensional unit matrix eye(13). The input image vector is then assigned to the class corresponding to the maximum output.
==================================================================
Greg Heath
Greg Heath 2011-12-19
...continued
>3-net.performFcn='msereg'; net.performParam.ratio=0.5;
Why MSEREG?? Why not use as many defaults as possible?
>if i keep the default my accuracy and regression will R=0.333 and the accuracy 90 but if i use net.performFcn='msereg' the R =.6999 and the accuracy 96%
Something is wrong somewhere.
How is R defined? Square root of the coefficient of determination (See Wikipedia)?
Try the default again with the columnized image inputs and unit matrix column outputs
===================================
4-net.trainParam.goal = 1e-5;
Why 1e-5??
> its the best value i can get better performance result through .
No need to search for a suitable value. Just choose a goal for R. Then work backwords to find the corresponding goal for MSE.
======================================================
5->[net,tr]=train(net,p,t); > a = sim(net,p); e = a-t;
Why not [net, tr, a, e] = ... ?
what is the wrong with my code why yours is better ?
Nothing is wrong with your code. Just letting you know that the additional code and computations are unnecessary.
===================================================
6->rmse = sqrt(mse(e)); acc=1-rmse
Useless scale-dependent performance index. Use R^2.
> what is R^2?
A common statistical measure of fit. Look up coefficient of determination in Wikipedia.
============================
Hope this helps
Greg
Mo al
Mo al 2011-12-20
hi sir , is thiers any way i can make the NN take the input (p) as a row instead of column? thank u sir
  2 个评论
Walter Roberson
Walter Roberson 2011-12-20
No. If your variable is the wrong way around, transpose it as you pass it in, using p.' or transpose(p)

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by