I am trying to build a neural network to classify data, my data are thousands of txt files, every file represent a 2D dimensional array with values 1 or -1, every array represent one configuration, and the labels that I should have are just two labels
I need a startup code snippet that build the network and train it
What I have tried:
I converted all of these txt files into images of black and white, and I used ML.NET through VS to train a network that is already built (I don't know anything about the structure of this network, it is hidden) then I wrote code to test it and it works very good
but this is nit what I need, I need to classify them without the need to convert them to images, and I want to build my own neural network, that I can control its structure at any point
Note: I just started this field, don't blame me if you find my question is very naïve or simple