Package Bio :: Package NeuralNetwork :: Package BackPropagation :: Module Layer :: Class AbstractLayer
[show private | hide private]
[frames | no frames]

Class AbstractLayer

Known Subclasses:
HiddenLayer, InputLayer, OutputLayer

Abstract base class for all layers.
Method Summary
  __init__(self, num_nodes, has_bias_node)
Initialize the layer.
  __str__(self)
Debugging output.
  set_weight(self, this_node, next_node, value)
Set a weight value from one node to the next.

Method Details

__init__(self, num_nodes, has_bias_node)
(Constructor)

Initialize the layer.

Arguments:

o num_nodes -- The number of nodes that are contained in this layer.

o has_bias_node -- Specify whether or not this node has a bias node. This node is not included in the number of nodes in the network, but is used in constructing and dealing with the network.

__str__(self)
(Informal representation operator)

Debugging output.

set_weight(self, this_node, next_node, value)

Set a weight value from one node to the next.

If weights are not explicitly set, they will be initialized to random values to start with.

Generated by Epydoc 2.1 on Thu Aug 10 20:01:04 2006 http://epydoc.sf.net