Dann Object

Back to Home

Import

const Dann = require('dannjs').dann;

Contructor( inputSize , outputSize )

When you create a neural network, you need to specify the size of the input & output layers.

const nn = new Dann(2,2);

Object Properties

• arch
  

  This value represents the architecture of the model in the form of an array.

• lr
  

  This defines the learning rate of the model. This value is set to 0.001 by default.

• epoch

  This is an empty value. This is meant for you to increase whenever you have completed one epoch. This serves as a way to save the number of epochs along with the weights in the dannData.json file.

• loss
  

  This is the most recent loss value of the model. If the model has never been trained before, this value will be set to 0.

Function properties

Model Creation

• addHiddenLayer
  
• outputActivation
  
• makeWeights
  
• setLossFunction

Model Interaction

• feedForward
  
• backpropagate

Weight Mutations

• mutateAdd
  
• mutateRandom

Save & load

• save (Browser)
  
• save (Nodejs)
  
• load (Browser)
  
• load (Nodejs)

Save & load JSON

• toJSON
  
• fromJSON
  

Deprecation warning : dataObject( ) & applyToModel() are deprecated as of v2.2.4f

Static

• createFromJSON
  

Debug

• log

Example

Here is a neural network training to solve XOR:

const Dann = require('dannjs').dann;  //nodejs only

// 128 input , 8 output Model with 3 hidden layers
const nn =  new Dann(128,8);

nn.addHiddenLayer(64,'leakyReLU');
nn.addHiddenLayer(32,'leakyReLU');
nn.addHiddenLayer(16,'tanH');

nn.makeWeights();

nn.outputActivation('sigmoid');
nn.setLossFunction('mae');

nn.lr = 0.01;

nn.log();