Skip to content

Latest commit

 

History

History
34 lines (20 loc) · 985 Bytes

README.md

File metadata and controls

34 lines (20 loc) · 985 Bytes

Neural Network: Multilayer Perceptron - Godot Engine

To solve non-linear problems, we need to connect several perceptrons together to create a neural network. In the example, the multilayer perceptron resolve a XOR operation.

The inputs will be propagated between several layers of perceptrons and output a value as a result.

See also my projects :

How to use

Create a new neural network with his number of inputs, hidden layers and outputs.

var neural_network = NeuralNetwork.new(INPUTS, HIDDEN_LAYERS, OUPUTS)

To train the neural network, pass the input values and the expected result to the training function.

neural_network.train([INPUT_1, INPUT_X...], EXEPTED_RESULT)

Dependencies

This project require Godot Engine 3.3.

Licenses

  • The source code is available under the MIT license.