Skip to content

A easy-to-use/create for a template NeuralNetwork that can be personalized for various uses.

Notifications You must be signed in to change notification settings

kudonon/NeuralNetwork

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is a standard one hidden-layer Neural Network created for multiple uses. It can be used with a variable number of inputs and variable number of neurons in the hidden layer.

For a personalized use, a couple of variables will have to changed to match demand.

First, change the trainingData 2D vector in main() to match the desired training data with how many ever variables you want. Second, change the realValues to reflect the expected outcome of the training data Third, create the desired Neurons in the hidden layer in addition to the output Neuron. Fourth, decide the number of mathematical and computational iterations you want the network to perform in addition to the desired interval for a console feedback on the status. Fifth, change/create additional Test Cases with input values to test/ evaluate the trained neural network

Lastly, run 'make' on shell and the Neural Network will be in session!

Enjoy!