Multi Hidden Layer Support (another proposal)

[maksuel]

I refactoried the entire nn.js code.

NO CONFLICTS

Please, do not hesitate to improve! Reference: #61 EXAMPLE: https://maksuel.github.io/Toy-Neural-Network-JS/examples/doodle_classification/ (the example use 2 hidden layers)

/**

• Constructor method.
• The user can enter with parameters (integer) to create a new NeuralNetwork,
• where: the first parameter represents the number of inputs, the second
• (or more) parameter represents the number of hidden nodes and the last
• parameter represents the number of outputs of the network.
• The user can copy an instance of NeuralNetwork by passing the same as an
• argument to the constructor.
• @param {NeuralNetwork|...Integer} args (Rest parameters) */

[Versatilus]

We would like to integrate something like this hopefully in the near future. Dan would like to do a little bit more in his streams with the simplified network first.

I'm curious why you chose to store the weights in a separate array instead of storing them in the layer objects.

[maksuel]

Vesatilus,

I was looking for a more semantic way to store the variables. That was the beginning of code refactoring. I just updated the project in the most semantic way I found, made it easier to read the methods and reduce the amount of loops.