public bool PerformIntegrityCheck()
{
// We will always have at least a bias and an output.
int count = _nodeList.Count;
if(count < 2) {
Debug.WriteLine(string.Format("Node list has less than the minimum number of neuron genes [{0}]", count));
return false;
}
// Check bias neuron.
if(NodeType.Bias != _nodeList[0].NodeType) {
Debug.WriteLine("Missing bias gene");
return false;
}
if(0u != _nodeList[0].Id) {
Debug.WriteLine(string.Format("Bias neuron ID != 0. [{0}]", _nodeList[0].Id));
return false;
}
// Check input nodes.
uint prevId = 0u;
int idx = 1;
for(int i=0; i<_inputNodeCount; i++, idx++)
{
if(NodeType.Input != _nodeList[idx].NodeType) {
Debug.WriteLine(string.Format("Invalid node type. Expected Input, got [{0}]", _nodeList[idx].NodeType));
return false;
}
if(_nodeList[idx].Id <= prevId) {
Debug.WriteLine("Input node is out of order and/or a duplicate.");
return false;
}
prevId = _nodeList[idx].Id;
}
// Check output neurons.
for(int i=0; i<_outputNodeCount; i++, idx++)
{
if(NodeType.Output != _nodeList[idx].NodeType) {
Debug.WriteLine(string.Format("Invalid node type. Expected Output, got [{0}]", _nodeList[idx].NodeType));
return false;
}
if(_nodeList[idx].Id <= prevId) {
Debug.WriteLine("Output node is out of order and/or a duplicate.");
return false;
}
prevId = _nodeList[idx].Id;
}
// Check hidden neurons.
// All remaining neurons should be hidden neurons.
for(; idx<count; idx++)
{
if(NodeType.Hidden != _nodeList[idx].NodeType) {
Debug.WriteLine(string.Format("Invalid node type. Expected Hidden, got [{0}]", _nodeList[idx].NodeType));
return false;
}
if(_nodeList[idx].Id <= prevId) {
Debug.WriteLine("Hidden node is out of order and/or a duplicate.");
return false;
}
prevId = _nodeList[idx].Id;
}
// Check connections.
count = _connectionList.Count;
if(0 == count)
{ // At least one connection is required, connectionless genomes are pointless.
Debug.WriteLine("Zero connections.");
return false;
}
// Check for multiple connections between nodes.
// Build a dictionary of connection endpoints.
Dictionary<ConnectionEndpointsStruct, object> endpointDict = new Dictionary<ConnectionEndpointsStruct,object>(count);
foreach(NetworkConnection conn in _connectionList)
{
ConnectionEndpointsStruct key = new ConnectionEndpointsStruct(conn.SourceNodeId, conn.TargetNodeId);
if(endpointDict.ContainsKey(key))
{
Debug.WriteLine("Connection error. A connection between the specified endpoints already exists.");
return false;
}
endpointDict.Add(key, null);
}
// Integrity check OK.
return true;
}
/// <summary>
/// Create a network definition by querying the provided IBlackBox (typically a CPPN) with the
/// substrate connection endpoints.
/// </summary>
/// <param name="blackbox">The HyperNEAT CPPN that defines the strength of connections between nodes on the substrate.</param>
/// <param name="lengthCppnInput">Optionally we provide a connection length input to the CPPN.</param>
public INetworkDefinition CreateNetworkDefinition(IBlackBox blackbox, bool lengthCppnInput)
{
// Get the sequence of substrate connections. Either a pre-built list or a dynamically
// generated sequence.
IEnumerable<SubstrateConnection> connectionSequence = _connectionList ?? GetConnectionSequence();
// Iterate over substrate connections. Determine each connection's weight and create a list
// of network definition connections.
ISignalArray inputSignalArr = blackbox.InputSignalArray;
ISignalArray outputSignalArr = blackbox.OutputSignalArray;
ConnectionList networkConnList = new ConnectionList(_connectionCountHint);
int lengthInputIdx = inputSignalArr.Length - 1;
foreach(SubstrateConnection substrateConn in connectionSequence)
{
int layerToLayerAdder = ((int)substrateConn._tgtNode._position[2] * 3);
// Assign the connection's endpoint position coords to the CPPN/blackbox inputs. Note that position dimensionality is not fixed.
for(int i=0; i<_dimensionality - 1; i++)
{
inputSignalArr[i] = substrateConn._srcNode._position[i];
inputSignalArr[i + _dimensionality - 1] = substrateConn._tgtNode._position[i];
inputSignalArr[i + 2 * (_dimensionality - 1)] = Math.Abs(substrateConn._srcNode._position[i] - substrateConn._tgtNode._position[i]);
}
// Optional connection length input.
if(lengthCppnInput) {
inputSignalArr[lengthInputIdx] = CalculateConnectionLength(substrateConn._srcNode._position, substrateConn._tgtNode._position);
}
// Reset blackbox state and activate it.
blackbox.ResetState();
blackbox.Activate();
// Read connection weight from output 0.
double weight = outputSignalArr[0 + layerToLayerAdder];
// Skip connections with a weight magnitude less than _weightThreshold.
double weightAbs = Math.Abs(weight);
if (outputSignalArr[2 + layerToLayerAdder] >= 0)
{
// For weights over the threshold we re-scale into the range [-_maxWeight,_maxWeight],
// assuming IBlackBox outputs are in the range [-1,1].
weight = (weightAbs) * _weightRescalingCoeff * Math.Sign(weight);
// Create network definition connection and add to list.
networkConnList.Add(new NetworkConnection(substrateConn._srcNode._id,
substrateConn._tgtNode._id, weight));
}
}
// Additionally we create connections from each hidden and output node to a bias node that is not defined at any
// position on the substrate. The motivation here is that a each node's input bias is independent of any source
// node (and associated source node position on the substrate). That we refer to a bias 'node' is a consequence of how input
// biases are handled in NEAT - with a specific bias node that other nodes can be connected to.
int setCount = _nodeSetList.Count;
for(int i=1; i<setCount; i++)
{
SubstrateNodeSet nodeSet = _nodeSetList[i];
foreach(SubstrateNode node in nodeSet.NodeList)
{
// Assign the node's position coords to the blackbox inputs. The CPPN inputs for source node coords are set to zero when obtaining bias values.
for(int j=0; j<_dimensionality - 1; j++)
{
inputSignalArr[j] = 0.0;
inputSignalArr[j + _dimensionality - 1] = node._position[j];
}
// Optional connection length input.
if(lengthCppnInput) {
inputSignalArr[lengthInputIdx] = CalculateConnectionLength(node._position);
}
// Reset blackbox state and activate it.
blackbox.ResetState();
blackbox.Activate();
// Read bias connection weight from output 1.
double weight = outputSignalArr[1+ (i- 1) * 3];
// Skip connections with a weight magnitude less than _weightThreshold.
double weightAbs = Math.Abs(weight);
if(weightAbs > _weightThreshold)
{
// For weights over the threshold we re-scale into the range [-_maxWeight,_maxWeight],
// assuming IBlackBox outputs are in the range [-1,1].
weight = (weightAbs - _weightThreshold) * _weightRescalingCoeff * Math.Sign(weight);
// Create network definition connection and add to list. Bias node is always ID 0.
networkConnList.Add(new NetworkConnection(0, node._id, weight));
}
}
}
// Check for no connections.
// If no connections were generated then there is no point in further evaulating the network.
// However, null is a valid response when decoding genomes to phenomes, therefore we do that here.
if(networkConnList.Count == 0) {
return null;
}
// Construct and return a network definition.
NetworkDefinition networkDef = new NetworkDefinition(_inputNodeCount, _outputNodeCount,
_activationFnLibrary, _netNodeList, networkConnList);
// Check that the definition is valid and return it.
Debug.Assert(networkDef.PerformIntegrityCheck());
return networkDef;
}