| Class | Description |
|---|---|
| AdamTrainer |
The Adaptive Moment Estimation trainer.
|
| BackpropTrainer |
The plain back-propagation trainer.
|
| CrossEntropy |
The square error function is the default for training.
|
| HebbTrainer |
The Hebbian trainer is of more theoretical importance, as it simply uses the basic Hebb update rule to change
the weights and biases of the net.
|
| HopfieldDeltaTrainer |
Trainer for Hopfield networks using the delta learning rule.
|
| LVQTrainer |
The Learning Vector Quantization training.
|
| NetError |
Collection of Neural network error measurements.
|
| RMSpropTrainer |
The Root Mean Square propagation trainer.
|
| RpropTrainer |
The Resilient Back-propagation trainer.
|
| SAETrainer |
The SAE trainer can transform a regular feed-forward network into a stacked auto-encoder.
|
| SOMTrainer |
The unsupervised SOM training algorithm implementing a simple dot product SOM with a linearly decreasing learn rate
and a linearly decreasing neighborhood radius.
|
| SquareError |
The square error function is the default for training.
|
| TrainingSignalGenerator |
This generator computes error signals for back-propagation and network errors.
|
This package contains a number of basic training algorithms for Boone.
There is a BackpropTrainer which implements
backpropagation training, optionally with momentum. The
RpropTrainer is a backpropagation variant,
which usually converges much faster.
The HopfieldDeltaTrainer is an iterative training
algorithm for generalized Hopfield networks.