public void FromIntList(IEnumerator <int> list)
{
subnetNeurons = list.Current;
list.MoveNext();
layers = list.Current;
list.MoveNext();
baseConnNum = list.Current;
list.MoveNext();
inputOutputConnNum = list.Current;
list.MoveNext();
EmotionState = list.Current;
list.MoveNext();
Init();
subNets = new NeuronCluster[list.Current];
list.MoveNext();
for (int i = 0; i < subNets.Length; i++)
{
subNets[i] = NeuronCluster.FromIntList(list);
}
connections = new NNConnection[list.Current];
list.MoveNext();
for (int i = 0; i < connections.Length; i++)
{
connections[i] = NNConnection.FromIntList(list);
}
}
public NeuralNetwork Read()
{
NeuralNetwork net;
using (BinaryReader reader = new BinaryReader(new FileStream(fileName, FileMode.Open)))
{
reader.BaseStream.Seek(0x18600, SeekOrigin.Begin);
double learningRate = reader.ReadDouble();
net = new NeuralNetwork(learningRate);
int layersCount = reader.ReadInt32();
NNLayer layer = null;
for (int i = 0; i < layersCount; i++)
{
string layerName = ReadString(reader);
layer = new NNLayer(layer);
net.Layers.Add(layer);
int neuronsCount = reader.ReadInt32();
int weightsCount = reader.ReadInt32();
for (int j = 0; j < neuronsCount; j++)
{
string neuronName = ReadString(reader);
NNNeuron neuron = new NNNeuron();
layer.Neurons.Add(neuron);
int connectionsCount = reader.ReadInt32();
for (int k = 0; k < connectionsCount; k++)
{
uint neuronIndex = reader.ReadUInt32();
uint weightIndex = reader.ReadUInt32();
NNConnection connection = new NNConnection(neuronIndex, weightIndex);
neuron.Connections.Add(connection);
}
}
for (int j = 0; j < weightsCount; j++)
{
string weightName = ReadString(reader);
double value = reader.ReadDouble();
NNWeight weight = new NNWeight {
Value = value
};
layer.Weights.Add(weight);
}
}
}
return(net);
}
public static NNConnection FromIntList(IEnumerator <int> list)
{
NNConnection result = new NNConnection();
result.srcNet = list.Current;
list.MoveNext();
result.srcIdx = list.Current;
list.MoveNext();
result.destNet = list.Current;
list.MoveNext();
result.destIdx = list.Current;
list.MoveNext();
return(result);
}
public void DoTimestep()
{
if (EmotionState > 0)
{
EmotionState--;
}
else if (EmotionState < 0)
{
EmotionState++;
}
int finalEmotionState = (EmotionState > EMOTION_MAGNITUDE_THRESH ? 1 : (EmotionState < -EMOTION_MAGNITUDE_THRESH ? -1 : 0));
// First, copy inputs / connection values into all subnets
for (int i = 0; i < connections.Length; i++)
{
NNConnection conn = connections[i];
NeuronCluster srcNet = subNets[conn.srcNet];
// destNet can be -1, which means access the IO ports
if (conn.destNet >= 0)
{
NeuronCluster destNet = subNets[conn.destNet];
srcNet.SetExternalInput(conn.srcIdx, destNet.GetExternalOutput(conn.destIdx));
destNet.SetExternalInput(conn.destIdx, srcNet.GetExternalOutput(conn.srcIdx));
}
else
{
srcNet.SetExternalInput(conn.srcIdx, inputVector[conn.destIdx]);
// copy outputs after processing
// outputVector[conn.destIdx] = srcNet.GetExternalOutput(conn.srcIdx);
}
}
// Second, subnets process based on emotional state
for (int i = 0; i < subNets.Length; i++)
{
subNets[i].FullTimestep(finalEmotionState);
}
// Third, set outputs
for (int i = 0; i < connections.Length; i++)
{
NNConnection conn = connections[i];
// destNet must be -1
if (conn.destNet != -1)
{
continue;
}
NeuronCluster srcNet = subNets[conn.srcNet];
outputVector[conn.destIdx] = srcNet.GetExternalOutput(conn.srcIdx);
}
}