how do i train this image pixels row by row i have one filtered image and original image i have to compare oringinal image first row and filtered image first row

 i=imread('le.jpg');
gray = rgb2gray(i);
isp=imnoise(gray,'salt & pepper',0.1);
ip=imnoise(gray,'poisson');
ip=imnoise(isp,'poisson');
med=medfilt2(ip);
inputs=im2double(med);
outputs=im2double(gray);
net = network( ...
1, ... % numInputs, number of inputs,
2, ... % numLayers, number of layers
[1; 0], ... % biasConnect, numLayers-by-1 Boolean vector,
[1; 0], ... % inputConnect, numLayers-by-numInputs Boolean matrix,
[0 0; 1 0], ... % layerConnect, numLayers-by-numLayers Boolean matrix
[0 1] ... % outputConnect, 1-by-numLayers Boolean vector
);
net.layers{1}.size = 256;
net.layers{1}.transferFcn = 'logsig';