# convolutional deep Neural Networks for matrix

I have a basic question about using convolutional neural networks. It's not my field but I'd like to read and understand about it.

What I know that convolutional neural networks is used for image processing, it means that we have an image as input and then the output should be the equivalent of that image. I was wondering what's about if I have a matrix containing numbers and zeros as inputs as below example :

so, is it possible in that case to use the conventional neural networks to detect each element and get the equivalent outputs?

For example, the order of numbers in every row in the above matrix should be changed, resulting 2^10 - 1 combinations. So I need to output to be 9 bits, which are 000000000 equivalent to first combination, and 000000001 equivalent to second, and so on till 111111111, and that should be for all rows too.

NP: I'm still at beginning of reading about that, if you have any link or videos explaining that in easy way (with Matlab is better than python), that will be appreciated.

• I am not sure that I understand you correctly, do you have an example of the desired input/output behavior? – Irreducible Sep 4 '19 at 8:19
• @Irreducible Thank you for your feedback, .. for example suppose that we have four values 0.7 , -0.7 , 0.3 and -0.3 and 0 means non of them is exist .. they are ordered in each rows in random way, for example in first row [0.7 0 0 -0.7 0.7 0 0.3 0 0 0] second row [0 -0.3 0.7 0 -0.7 0.3 0 0 0.3 0] and so on, resulting 2^8 possibilities, so the output should be equivalent to every combination. for example first combination output should be 10000000 and second 01000000 and so on. hope it clear now, I will modify the question too – Gze Sep 4 '19 at 8:42