Neural Network help

Okay so basically, I’m using a specific Module: Module

and then I’ve been looking at the code. Including the contents of the module. But a lot of the variables are hard to understand. The forum link: Neural Network Library (Obsolete)

I’m already aware that createNet makes the network, Savenet grabs the AI progress with JSON encoding.

so the question is what are the arguments for:

module.forwardNet

and

module.backwardNet

If I posted this topic wrong, please let me know, this is my first post

There is a documentation section that you have to collapse to see the information on how to use each function. For example, forwardNet has this:

module.forwardNet(network, inputs, giveCache)

local network = module.createNet(2, 2, 3, 1)
local out = module.forwardNet(network, {1,4}) [1]
--Value types:
--forwardNet(array/NETWORK, array, boolean [OPTIONAL])

Just a note, try to not base any systems off of this module. It is old (by my standards) and it is quite horribly written. I am in the process of making a proper OOP library soon enough that will make this one obsolete.
Feel free to use it for testing, practice, or educational purposes though.

2 Likes

Thanks,

a small question about the arguments though, what does the table and the [1] in forwardNet do?

and WOW, you were the one who made that! Awesome!