How to interpret Neural Network output if it is NaN?
조회 수: 2 (최근 30일)
이전 댓글 표시
Code to classify output into 3 classes- 0,1 and 2 (indicating no fault, line fault and irradiance fault). Output shows NaN and -0.00
Code:
% code
filename= 'new_3classes_Modif_NEURAL_NET_INPUT.xlsx';
S= xlsread (filename, 'B3:B106');
T= xlsread (filename, 'C3:C106');
V= xlsread (filename, 'D3:D106');
I= xlsread (filename, 'E3:E106');
P= xlsread (filename, 'G3:F106');
O= xlsread (filename, 'H3:G106');
C = [S T V I P];
x= transpose (C);
t = O.';
net = cascadeforwardnet(10);
net = configure(net,x,t);
y1 = net(x);
net = train(net,x,t);
y2 = net(x);
plotconfusion (t,y2);
end
댓글 수: 0
답변 (1개)
Greg Heath
2017년 4월 23일
For classification into mutually exclusive classes, the target columns should be [0,1] unit vectors. For examples, search the NEWSGROUP and ANSWERS using:
greg patternnet
and
greg patternnet tutorial
Hope this helps.
Thank you for formally accepting my answer
Greg
댓글 수: 0
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!