How to set the target vector for image input in training neural network?

I am training a neural network to recognize traffic sign(stop sign). I have taken 90 images of size 8x8 of which 30 are positive and remaining are negative. So my input is 64x90 and my target vector is 1x90. But what will be the values in my target vector? How do i assign it?

Answer 1

[Greg Heath]

There are two choices

1-dimensional target 0 or 1

2-dimensional target [ 1;0 ] or [ 0;1 ]

The 2-D target is preferred because it is a special case of a c-class target matrix with columns of the unit matrix eye(c) as the target vectors.

Hope this helps.

Thank you for formally accepting my answer

Greg

PS I have zillions of pattern recognition/classifier examples in the NEWSGROUP and ANSWERS

Search using

 GREG PATTERNNET

[Amod Amatya]

I am a bit confused.. Previously, i have assigned target = 1x90 matrix (first 30 column = 1 and last 60 column = 0) as the first 30 are positive images. Is this correct?