public void BackPropogate(NetworkState last, NetworkState now)
{
for (int i = states.Count - 1; i >= 0; i--)
{
object state = states[i];
Layer layer = Network.Layers[i];
RecurrentLayer recurrentLayer = layer as RecurrentLayer;
FeedForwardLayer feedForwardLayer = layer as FeedForwardLayer;
if (recurrentLayer != null)
{
RecurrentTrainingState recurrentState = (RecurrentTrainingState)state;
recurrentState.Last = (RecurrentState)last.states[i];
recurrentState.Now = (RecurrentState)now.states[i];
recurrentLayer.BackPropogate(recurrentState);
}
else
{
FeedForwardTrainingState feedForwardState = (FeedForwardTrainingState)state;
feedForwardState.Now = (FeedForwardState)now.states[i];
feedForwardLayer.BackPropogate(feedForwardState);
}
}
}
/// <summary>
/// Creates a Recurrent Neural Network with the specified number of layers and one output Neuron.
/// </summary>
/// <param name="layerSize"></param>
public RecurrentNetwork(NetworkConfiguration configuration, params int[] layerSize)
{
this.Configuration = configuration;
configuration.InitialiseRandom();
layers = new Layer[layerSize.Length];
for (int i = 0; i < layers.Length - 1; i++)
{
//layers[i] = new FeedForwardLayer(layerSize[i + 1], layerSize[i]);
layers[i] = new RecurrentLayer(configuration, layerSize[i + 1], layerSize[i]);
}
layers[layers.Length - 1] = new FeedForwardLayer(configuration, 1, layerSize[layerSize.Length - 1]);
}
