MATLAB Neural Network - Forward Propagation

조회 수: 5 (최근 30일)
Erica Dos Santos Saraiva
Erica Dos Santos Saraiva 2021년 7월 24일
댓글: Erica Dos Santos Saraiva 2021년 7월 28일
I am trying to implement a forward propogation with a foor loop as advices on neural smithing. I keep recieveing an error when iterating through my for loop. How do I get rid of this error.
I have checked the sizes for both NOUTPUTS(i+1) and NPATS(i) which both are = 1 however keep receiving this error.
Patterns = x'; Desired = y; NHIDDENS = 1; prnout=Desired;
% Patterns become x so number of inputs becomes size of patterns
[NINPUTS,NPATS] = size(Patterns); [NOUTPUTS,NP] = size(Desired);
%apply the backprop here...
LearnRate = 0.15; Momentum = 0; DerivIncr = 0; deltaW1 = 0; deltaW2 = 0;
% Keeps the tan ordering of the examples of x
Inputs1= [Patterns;ones(1,NPATS)]; %Inputs1 = [ones(1,NPATS); Patterns];
% Weight initialisation
Weights1 = 0.5*(rand(NHIDDENS,1+NINPUTS)-0.5);
Weights2 = 0.5*(rand(1,1+NHIDDENS)-0.5);
TSS_Limit = 0.02;
for epoch = 1:10
for ii = 0: ii < length(NINPUTS)
NOUTPUTS(ii+1) = NPATS(ii);
% Sets bias to 1
NOUTPUTS(1) = 1;
for ii = NHIDDENS: ii < NINPUTS
sum = 0;
for ij = 0: ij < ii
sum = sum + deltaW1(ii,ij) * NOUTPUTS(ij);
NOUTPUTS(ii) = tanh(sum);
Unable to perform assignment because the
left and right sides have a different
number of elements.
Error in mlpts (line 66)

답변 (1개)

Swetha Polemoni
Swetha Polemoni 2021년 7월 27일
You might want to check on the format of for loops you have used(for ii = 0: ii < length(NINPUTS)). This can be replaced with following code snippet.
ii = intial value;
while condition
  댓글 수: 1
Erica Dos Santos Saraiva
Erica Dos Santos Saraiva 2021년 7월 28일
Do you know how to implement a for loop for forward propogation?

댓글을 달려면 로그인하십시오.


Help CenterFile Exchange에서 Image Data Workflows에 대해 자세히 알아보기


Community Treasure Hunt

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

Start Hunting!

Translated by