Neural is a simple Multi-layer-perceptron (MLP). Neurons are supervised by a algorithm (back-propagation here).
Neural v1.0 works fine.
It's a basic version, for changing inputs and output, we need go to neural.c and neural.h
to modify neurons values.
https://stevenmiller888.github.io/mind-how-to-build-a-neural-network/
http://www.dataminingmasters.com/uploads/studentProjects/NeuralNetworks.pdf
https://www.cs.swarthmore.edu/~meeden/cs81/s10/BackPropDeriv.pdf
http://fbim.fh-regensburg.de/~saj39122/jfroehl/diplom/e-13-text.html#Backpropagation
For multi-layers-perceptron:
https://web.archive.org/web/20150317210621/https://www4.rgu.ac.uk/files/chapter3%20-%20bp.pdf
nn.c provide a full array-based neural network. Based on most simply neural architecture:
3 layers : input, hidden, output.
For the other files, it's my personnal interpretation of a simple neural network. Build on linked list and inspire from nn.c and other stuff on the web.