/// <summary>
/// Generate a Jordan neural network.
/// </summary>
/// <returns>A Jordan neural network.</returns>
public BasicNetwork Generate()
{
// construct an Jordan type network
ILayer input = new BasicLayer(this.activation, false,
this.inputNeurons);
ILayer hidden = new BasicLayer(this.activation, true,
this.hiddenNeurons);
ILayer output = new BasicLayer(this.activation, true,
this.outputNeurons);
ILayer context = new ContextLayer(this.outputNeurons);
BasicNetwork network = new BasicNetwork();
network.AddLayer(input);
network.AddLayer(hidden);
network.AddLayer(output);
output.AddNext(context, SynapseType.OneToOne);
context.AddNext(hidden);
int y = PatternConst.START_Y;
input.X = PatternConst.START_X;
input.Y = y;
y += PatternConst.INC_Y;
hidden.X = PatternConst.START_X;
hidden.Y = y;
context.X = PatternConst.INDENT_X;
context.Y = y;
y += PatternConst.INC_Y;
output.X = PatternConst.START_X;
output.Y = y;
network.Structure.FinalizeStructure();
network.Reset();
return network;
}
/// <summary>
/// Load the specified Encog object from an XML reader.
/// </summary>
/// <param name="xmlIn">The XML reader to use.</param>
/// <returns>The loaded object.</returns>
public IEncogPersistedObject Load(ReadXML xmlIn)
{
int neuronCount = 0;
int x = 0;
int y = 0;
double biasActivation = 1;
String threshold = null;
IActivationFunction activation = null;
String end = xmlIn.LastTag.Name;
String context = null;
while (xmlIn.ReadToTag())
{
if (xmlIn.IsIt(BasicLayerPersistor.TAG_ACTIVATION, true))
{
xmlIn.ReadToTag();
String type = xmlIn.LastTag.Name;
activation = BasicLayerPersistor.LoadActivation(type, xmlIn);
}
else if (xmlIn.IsIt(BasicLayerPersistor.PROPERTY_NEURONS, true))
{
neuronCount = xmlIn.ReadIntToTag();
}
else if (xmlIn.IsIt(BasicLayerPersistor.PROPERTY_X, true))
{
x = xmlIn.ReadIntToTag();
}
else if (xmlIn.IsIt(BasicLayerPersistor.PROPERTY_Y, true))
{
y = xmlIn.ReadIntToTag();
}
else if (xmlIn.IsIt(BasicLayerPersistor.PROPERTY_THRESHOLD, true))
{
threshold = xmlIn.ReadTextToTag();
}
else if (xmlIn.IsIt(PROPERTY_CONTEXT, true))
{
context = xmlIn.ReadTextToTag();
}
else if (xmlIn.IsIt(BasicLayerPersistor.PROPERTY_BIAS_ACTIVATION, true))
{
biasActivation = double.Parse(xmlIn.ReadTextToTag());
}
else if (xmlIn.IsIt(end, false))
{
break;
}
}
if (neuronCount > 0)
{
ContextLayer layer;
if (threshold == null)
{
layer = new ContextLayer(activation, false, neuronCount);
}
else
{
double[] t = NumberList.FromList(CSVFormat.EG_FORMAT, threshold);
layer = new ContextLayer(activation, true, neuronCount);
for (int i = 0; i < t.Length; i++)
{
layer.BiasWeights[i] = t[i];
}
}
if (context != null)
{
double[] c = NumberList.FromList(CSVFormat.EG_FORMAT, context);
for (int i = 0; i < c.Length; i++)
{
layer.Context[i] = c[i];
}
}
layer.X = x;
layer.Y = y;
layer.BiasActivation = biasActivation;
return layer;
}
return null;
}
/// <summary>
/// Generate the RSOM network.
/// </summary>
/// <returns>The neural network.</returns>
public BasicNetwork Generate()
{
ILayer output = new BasicLayer(new ActivationLinear(), false,
this.outputNeurons);
ILayer input = new BasicLayer(new ActivationLinear(), false,
this.inputNeurons);
BasicNetwork network = new BasicNetwork();
ILayer context = new ContextLayer(this.outputNeurons);
network.AddLayer(input);
network.AddLayer(output);
output.AddNext(context, SynapseType.OneToOne);
context.AddNext(input);
int y = PatternConst.START_Y;
input.X = PatternConst.START_X;
input.Y = y;
context.X = PatternConst.INDENT_X;
context.Y = y;
y += PatternConst.INC_Y;
output.X = PatternConst.START_X;
output.Y = y;
network.Structure.FinalizeStructure();
network.Reset();
return network;
}
