LibCapy - nnClassifier

Class implementing a classifier based on a fully connected neural network.

Macros:

Enumerations:

None.

Typedefs:

None.

Struct CapyNNClassifier :

Struct CapyNNClassifier's properties:

Inherits CapyClassifier

Reference to the definition of the neural network model

Neural network

Verbose mode (default: false)

Time available for training (in second, default: 60, no time limit if 0)

Number of iteration available for training (default: 0, no limit if 0)

Batch size for training (default: 100)

Counter for iteration during training

Step size for the gradient descent (default: 0.1)

Momentum for the gradient descent (default: 0.1)

Seed for the pseudo random generator (default: 0)

Best loss during training

Current gradient norm during training

Threshold to stop the training if the gradient is null (default: 1e-6)

Threshold to stop the training if the loss is null (default: 1e-6)

Dampening coefficient for the adaptative learning rate (default: 0.5)

Boosting coefficient for the adaptative learning rate (default: 1.1)

Struct CapyNNClassifier's methods:

Destructor

Initialise the parameters value

Input argument(s):

params: the array of parameters
Ouput: The array of parameters is updated

Function herited from the parent to export the body to HTML.

Input argument(s):

stream: the stream where to export
title: the title of the web app
dataset: the training dataset
expectedAccuracy: the expected accuracy of the classifier (in [0,1])

Output and side effect(s):

The and part of a ready to use web app implementing the classifier is written on the stream. The web app can be completed by calling exportToHtml on the classifier to write the