Neural Network |
This topic contains the following sections:
This section describes neural network models. Library supports next neural network types:
Multi-layer perceptron: classical multi-layer feed-forward network;
Deep Neural Network: the multi-layer feed-forward network with special train algorithm;
Autoencoder: one hidden layer network learned in an unsupervised manner.
The neural network model in the library utilizes the fast sigmoid activation function in all except last layers: .
The last layer uses linear activation function: .
By default the neural network models uses Cross Entropy for loss function estimation:
Also library allows to user set custom loss function. (See the CustomLoss property.)
By default model training procedure uses L1 regularization with default weight equals to 0.0001.
The default model stops training if the best objective value do not improves on more than 0.00001 in last 100 train steps.
But the user can adjust them with any OR combination of the next conditions:
Either TerminationIterations are have passed;
Either TerminationTimeout time have passed;
The TerminationObjectiveChange conditions are met: objective function best value do not improves on more than Epsilon value in last Interval steps.
In any case user can specify his own train stop delegate function via the TerminationDelegate property.
Next most important properties are featured in the FFNet class:
Property | Description |
---|---|
The list of classes in the model | |
The neural network model topology | |
Neural network L1 regularization parameter. |
Termination conditions properties:
Property | Description |
---|---|
The maximum optimization iterations number. Zero means infinite iterations. | |
The optimization algorithm timeout: the execution will be interrupted on the next step after the timeout expiration. | |
Objective function change stop criterion. Null means no objective change termination conditions. | |
Custom stop criterion function. |
Train statistics properties:
Property | Description |
---|---|
Last Train or Update operation best objective value. | |
Last Train or Update operation best step index. | |
Last Train or Update operation total steps number. |