In this module, a neural network is made up of multiple layers — hence the name multi-layer perceptron! You need to specify these layers by instantiating one of two types of specifications:
sknn.mlp.Layer
: A standard feed-forward layer that can use linear or non-linear activations.sknn.mlp.Convolution
: An image-based convolve operation with shared weights, linear or not.
In practice, you need to create a list of these specifications and provide them as the layers
parameter to the sknn.mlp.Regressor
or sknn.mlp.Classifier
constructors.
sknn.mlp.Layer
sknn.mlp.Convolution
Most of the functionality provided to simulate and train multi-layer perceptron is implemented in the (abstract) class sknn.mlp.MultiLayerPerceptron
. This class documents all the construction parameters for Regressor and Classifier derived classes (see below), as well as their various helper functions.
sknn.mlp.MultiLayerPerceptron
When using the multi-layer perceptron, you should initialize a Regressor or a Classifier directly.
See the class sknn.mlp.MultiLayerPerceptron
for inherited construction parameters.
sknn.mlp.Regressor
Also check the sknn.mlp.MultiLayerPerceptron
class for inherited construction parameters.
sknn.mlp.Classifier