#Hosing meta-layers
@include "Data.tz"

@use Abstract.
@use Matrix.
@use Vector.
@use Genome.

@use Mobile.

@define UTIL 0.
@define UTIL2 1.

Abstract : NeuralNetwork4 [version 2.3] {
    % An experimental neural network class for different types of neural
    % networks whose goal is to provide efficient computation and the
    % ability to manipulate the parameters and connections using evolution
    
    + variables:
        network (pointer).
        nodes (object).
        inputNodes (object).
        outputNodes (object).
        weights (object).
        connections (object).
        neuronCount (int).
        inputNeuronCount (int).
        outputNeuronCount (int).
        iterationStep (float).
        timeConstant (float).
        stateBoundLower (float).
        stateBoundUpper (float).
        
        homeland (string).
        fitness(double).
  	parentAfitness(double).
  	parentBfitness(double).
  	
  	meta-neuronCount(int).
  	meta-connectionCount(int).#count of under-net connections
  	meta-network(pointer).
  	meta-nodes(object).
  	meta-connections(object).
  	meta-weights(object).
  	hosing(int).
    + to destroy:
        if network: free network.
        if nodes: free nodes.
        if inputNodes: free inputNodes.
        if outputNodes: free outputNodes.
        if weights: free weights.
        if connections: free connections.
        if meta-connections: free meta-connections.
  	if meta-weights: free meta-weights.
  	if meta-nodes: free meta-nodes.
  	if meta-network: free meta-network.
        super destroy.
    + to init:
        iterationStep = 1.0.
        timeConstant = 1.0.
        parentAfitness = 0.
        parentBfitness = 0.
        fitness = 0.
        self disable-auto-free.
        
    + to init-with neuron-count theNetworkSize (int):
        network = neuralNetworkNew(theNetworkSize).
        neuronCount = theNetworkSize.
        #print "neuronCount $neuronCount".
        nodes = new Vector.
        nodes set-vector-pointer to neuralNetworkGetNeuronStateVector(network) with-size neuronCount.
        weights = new Matrix2D.
        weights set-matrix-pointer to neuralNetworkGetConnectionWeightMatrix(network) x-size neuronCount y-size neuronCount.
        connections = new Matrix2D.
        connections set-matrix-pointer to neuralNetworkGetConnectionStructureMatrix(network) x-size neuronCount y-size neuronCount.
        return self.
    + to init-meta-with neuron-count theNetworkSize (int) hose h(int): 
    	n(int).
	i(int).
	j(int).
        val(double).
        hosing = h.
	meta-connectionCount = ((neuronCount - 1) * (neuronCount - 1)).        
        if hosing == 0:{
	        meta-neuronCount = (neuronCount + meta-connectionCount).#((neuronCount + meta-connectionCount) / 2)
	} else {
		meta-neuronCount = (neuronCount * 4) + 1.
	}
        meta-network = neuralNetworkNew(meta-neuronCount).
        meta-nodes = new Vector.
        meta-nodes set-vector-pointer to neuralNetworkGetNeuronStateVector(meta-network) with-size meta-neuronCount.
        meta-weights = new Matrix2D.
        meta-weights set-matrix-pointer to neuralNetworkGetConnectionWeightMatrix(meta-network) x-size meta-neuronCount y-size meta-neuronCount.
        meta-connections = new Matrix2D.
        meta-connections set-matrix-pointer to neuralNetworkGetConnectionStructureMatrix(meta-network) x-size meta-neuronCount y-size meta-neuronCount.

	for i = 0, i < meta-neuronCount, i++:{
		for j = 0, j < meta-neuronCount, j++:{
        		if i != j:{
        			val = random[2.0] - 1.0.
        			meta-connections set-value to 1.0 at-x i at-y j.
        			meta-weights set-value to val at-x i at-y j.
        		}
        		else: meta-connections set-value to 0.0 at-x i at-y j.    		
        	}
        }
        return self.
        
    + to start-with-genome genome gene(object):
        n(int).
        m(int).
        o (int).
        val (double).
        neuronCount = gene get-size.
        network = neuralNetworkNew(neuronCount).
        nodes = new Vector.
        nodes set-vector-pointer to neuralNetworkGetNeuronStateVector(network) with-size neuronCount.
        weights = new Matrix2D.
        weights set-matrix-pointer to neuralNetworkGetConnectionWeightMatrix(network) x-size neuronCount y-size neuronCount.
        connections = new Matrix2D.
        connections set-matrix-pointer to neuralNetworkGetConnectionStructureMatrix(network) x-size neuronCount y-size neuronCount.
	print "Start with genome neuronCount $neuronCount".
        for m = 0, m  <  neuronCount, m++:{
            for o = 0, o < neuronCount, o++:{
                val = gene get-val at-x o at-y m.
                weights set-value to val at-x o at-y m.
            }
        }
	meta-neuronCount = gene get-meta-size.
	print " meta-neuronCount $meta-neuronCount ".
	if (meta-neuronCount):{
		meta-network = neuralNetworkNew(meta-neuronCount).
		meta-nodes = new Vector.
        	meta-nodes set-vector-pointer to neuralNetworkGetNeuronStateVector(meta-network) with-size meta-neuronCount.
        	meta-weights = new Matrix2D.
        	meta-weights set-matrix-pointer to neuralNetworkGetConnectionWeightMatrix(meta-network) x-size meta-neuronCount y-size meta-neuronCount.
        	meta-connections = new Matrix2D.
        	meta-connections set-matrix-pointer to neuralNetworkGetConnectionStructureMatrix(meta-network) x-size meta-neuronCount y-size meta-neuronCount.	
        	for m = 0, m  <  meta-neuronCount, m++:{
            		for o = 0, o < meta-neuronCount, o++:{
                	val = gene get-meta-val at-x o at-y m.
                	meta-weights set-value to val at-x o at-y m.
            		}
        	} 
        }
        self set-homeland of (gene get-homeland).
        self set-parentA to (gene get-parentA).
        self set-parentB to (gene get-parentB).
        self set-fitness to (gene get-fitness).
        
    - to get-network-pointer:
        return network.
    
    + to get-neuron-state-vector:
        return nodes.
    #+ to save-with-dialog:
    #    self archive-as-xml file fileName (string).
    #show-dialog with-title title (string) with-message message (string) with-yes-button yesString (string) with-no-button noString (string)
    + section "Network Parameter Accessors":
    + to get-genome:
        rtn (object).
        n (int).

        rtn = new NeuralGenome2.
        rtn set-weights of-matrix weights of-size neuronCount.
        if (meta-neuronCount):{
        	rtn set-meta-weights of-matrix meta-weights of-size meta-neuronCount.
        }
        rtn set-homeland of homeland.
        rtn set-parentA to parentAfitness.
        rtn set-parentB to parentBfitness.
        rtn set-fitness to fitness.
        return rtn.
    + to set-hosing to h (int):
    	hosing = h.
    + to get-neuron-count:
        return neuronCount.
    + to get-meta-neuron-count:
    	return meta-neuronCount.
        
    + to get-iteration-step:
        return iterationStep.
        
    + to set-iteration-step to newTimeStep (float):
        iterationStep = newTimeStep.
        neuralNetworkSetTimeStep(network, newTimeStep).
        neuralNetworkSetTimeStep(meta-network, newTimeStep). 
        
    + to get-time-constant:
        return timeConstant.
        
    + to set-time-constant to newTimeConstant (float):
        timeConstant = newTimeConstant.
        neuralNetworkSetTimeConstant(network, newTimeConstant).
        neuralNetworkSetTimeConstant(meta-network, newTimeConstant).
    + to get-lower-saturation-boundry:
        return stateBoundLower.
        
    + to get-upper-saturation-boundry:
        return stateBoundUpper.
    
    + to set-saturation-bounds between lower (float)
                                and upper (float):
        stateBoundLower = lower.
        stateBoundUpper = upper.
        neuralNetworkSetNeuronStateBounds(network, lower, upper).
        neuralNetworkSetNeuronStateBounds(meta-network, lower, upper).
    
    + section "Network State Variable and Vector Accessors":
        
    + to set-neuron-state at index (int) to value (float):
        neuralNetworkSetNeuronState(network, index, value).
        
    + to perturb-neuron-state at index (int) to value (float):
        oldVal(float).
        newVal(float).
        oldVal = neuralNetworkGetNeuronState(network, index).
        newVal = oldVal + value.
        if (newVal > 1):{
        	newVal = 1.
        }
        if (newVal < -1):{
        	newVal = -1.
        }
        # print "pertubing state $oldVal to $newVal at $index".
        neuralNetworkSetNeuronState(network, index, newVal).
        
    + to get-neuron-state at index (int):
        return neuralNetworkGetNeuronState(network, index).
        
    + to set-input-state-vector from first (int) to last (int):
    % returns a vector which contains the input nodes
        inputNodes = new Vector.
        inputNodes set-vector-pointer to neuralNetworkSetInputNeurons(network, first, (last - first)) with-size (last - first).
        inputNeuronCount = (last - first).
        return inputNodes.
        
    + to get-input-state-vector:
    % returns a vector which contains the input nodes
        return inputNodes.
    
    + to set-output-state-vector from first (int) to last (int):
    % returns a vector which contains the output nodes
        outputNodes = new Vector.
        outputNodes set-vector-pointer to neuralNetworkSetInputNeurons(network, first, (last - first)) with-size (last - first).
        outputNeuronCount = (last - first).
        return outputNodes.
                    
    + to get-output-state-vector:
    % returns a vector which contains the output nodes
        return outputNodes.

    + to get-connection-structure-matrix:
    % returns a matrix of synaptic connections [0,1]
        return connections.        
    
    + to apply-structure-to-weights:
        neuralNetworkApplyStructure(network).
        
    + to get-connection-weight-matrix:
    % returns a matrix of the synaptic strengths
        return weights.
        
    + to get-meta-connection-weight-matrix:
    	return meta-weights.
    	
    + to set-connection-weight-matrix to val (double) at-x i (int) at-y m (int):
    	if i != m:{
        	connections set-value to 1.0 at-x i at-y m.
        	weights set-value to val at-x i at-y m.
        }
        
    + to set-meta-connection-weight-matrix to val (double) at-x i (int) at-y m (int):
    	if i != m:{
        	meta-connections set-value to 1.0 at-x i at-y m.
        	meta-weights set-value to val at-x i at-y m.
        }
  
    + to get-weight at-x x (int) at-y y (int):
        return (weights get-value at-x x at-y y).

    + to get-meta-weight at-x x (int) at-y y (int):
        return (meta-weights get-value at-x x at-y y).
        
    + to perturb-weight to val(double) at-x x(int) at-y y (int):
    	tempval(double).
    	tempval = (weights get-value at-x x at-y y).
    	tempval = tempval + val.
    	weights set-value to tempval at-x x at-y y.
        
    + to get-edge at-x x (int) at-y y (int):
        return (connections get-value at-x x at-y y).
    
    + to randomize-states between lowerBound = -1.0 (float)
                           and upperBound = 1.0 (float):
        i (int).
        
        for i = 0, i < neuronCount, i++:
                    nodes set-value to (lowerBound + random[(upperBound - lowerBound)]) at-x i.
        
    + to randomize-weights between lowerBound = -1.0 (float)
                           and upperBound = 1.0 (float)
                           with-autapses autapsesBool = 0 (int):
        i, j (int).
        
        for i = 0, i < neuronCount, i++:
            for j = 0, j < neuronCount, j++:
                if autapsesBool:
                {
                    weights set-value to (lowerBound + random[(upperBound - lowerBound)]) at-x i at-y j.
                }
                else:
                {
                    if i == j: weights set-value to 0.0 at-x i at-y j.
                    else: weights set-value to (lowerBound + random[(upperBound - lowerBound)]) at-x i at-y j.
                }
     + to randomize-meta-weights between lowerBound = -1.0 (float)
                           and upperBound = 1.0 (float)
                           with-autapses autapsesBool = 0 (int):
        i, j (int).
        
        for i = 0, i < meta-neuronCount, i++:
            for j = 0, j < meta-neuronCount, j++:
                if autapsesBool:
                {
                    meta-weights set-value to (lowerBound + random[(upperBound - lowerBound)]) at-x i at-y j.
                }
                else:
                {
                    if i == j: meta-weights set-value to 0.0 at-x i at-y j.
                    else: meta-weights set-value to (lowerBound + random[(upperBound - lowerBound)]) at-x i at-y j.
                }               
    + to init-random-structure with-connectivity-percent thePercent = 0.5 (float) with-autapses autapsesBool = 0 (int):
        i, j (int).
        edge (int).
        
        for i = 0, i < neuronCount, i++:
            for j = 0, j < neuronCount, j++:
                if autapsesBool:
                {
                    if random[1.0] < thePercent:
                        edge = 1.0.
                    else:
                        edge = 0.0.
                    connections set-value to edge at-x i at-y j.
                }
                else:
                {
                    if i != j:
                    {
                        if random[1.0] < thePercent:
                            edge = 1.0.
                        else:
                            edge = 0.0.
                        connections set-value to edge at-x i at-y j.
                    }
                    else: connections set-value to 0.0 at-x i at-y j.
                }
     + to init-random-meta-structure with-connectivity-percent thePercent = 0.5 (float) with-autapses autapsesBool = 0 (int):
        i, j (int).
        edge (int).
        
        for i = 0, i < meta-neuronCount, i++:
            for j = 0, j < meta-neuronCount, j++:
                if autapsesBool:
                {
                    if random[1.0] < thePercent:
                        edge = 1.0.
                    else:
                        edge = 0.0.
                    meta-connections set-value to edge at-x i at-y j.
                }
                else:
                {
                    if i != j:
                    {
                        if random[1.0] < thePercent:
                            edge = 1.0.
                        else:
                            edge = 0.0.
                        meta-connections set-value to edge at-x i at-y j.
                    }
                    else: meta-connections set-value to 0.0 at-x i at-y j.
                }               
    + to init-fully-connected-structure with-autapses autapsesBool = 0 (int):
        i, j (int).
        
        for i = 0, i < neuronCount, i++:
            for j = 0, j < neuronCount, j++:
                if autapsesBool:
                {
                    connections set-value to 1.0 at-x i at-y j.
                }
                else:
                {
                    if i != j: connections set-value to 1.0 at-x i at-y j.
                    else: connections set-value to 0.0 at-x i at-y j.
                }
        
            
    + to update-state:
    % updates the network's state based on current state and
    % inputs
        neuralNetworkUpdateState(network).
    + to update-meta-state:
    	n (int).
	m (int).
	o (int).
	val (double).
    	oldval (double).
    	top (double).
    	select (int).
    	cnt (int).
        for n = 0, n < neuronCount, n++:{
		val = neuralNetworkGetNeuronState(network, n).
		oldval = neuralNetworkGetNeuronState(meta-network, n).
		val = val + oldval.
		neuralNetworkSetNeuronState(meta-network, n, val).
		#print " hosing NeuralNetork underlying num $n activated $val".
	}
	neuralNetworkUpdateState(meta-network).
	if (hosing == 0):{
		for n = 0, n < neuronCount, n++:{
			for m = 0, m < neuronCount, m++:{
				if n != m:{
					o = (meta-neuronCount - ((n * neuronCount) + m)).
					val = neuralNetworkGetNeuronState(meta-network, o).
					oldval = (weights get-value at-x n at-y m).
					val = val + oldval.
					if val > 1.0 : val = 1.0.
					if val < -1.0 : val = -1.0.
					weights set-value to val at-x n at-y m.
				}
			}
		}
	} else {
		#m = (meta-neuronCount - neuronCount - 1).
		#val = neuralNetworkGetNeuronState(meta-network, m).
		#m = (|val| * neuronCount) % neuronCount.
		top = 0.0.
		cnt = 0.
		select = 0.
		for n = (meta-neuronCount - ( 2 * neuronCount )), n < (meta-neuronCount - neuronCount), n++ :{
			val = neuralNetworkGetNeuronState(meta-network, n).
			if (val > top):{
				top = val.
				select = cnt.
			}
			cnt += 1.
		}
		for n = 0, n < neuronCount, n++:{
			o = (meta-neuronCount - (neuronCount) + n).
			val = neuralNetworkGetNeuronState(meta-network, o).
			oldval = (weights get-value at-x n at-y m).
			val = val + oldval.
			if val > 1.0 : val = 1.0.
			if val < -1.0 : val = -1.0.
			weights set-value to val at-x n at-y select.
			#print " hose is adressing $n and $select with value $val".
		}
	}			
			
		
    + to mutate:
        % Implement this method to mutate the genes of this object.  This method
        % must be implemented by your subclass.
        n (int).
        m (int).
        i (int).
        val(double).
        
        for i=0, i < 50, i++:{
            n = random[neuronCount - 1].
            m = random[neuronCount - 1].
            val = random[2.0]- 1.0.
            if m != n:{
                weights set-value to val at-x n at-y m.
            }
        }
        #die "The method \"mutate\" must be implemented in your GeneticAlgorithmIndividual subclass!".
    + to mutate-connections connects z(int):
        % Implement this method to mutate the genes of this object.  This method
        % must be implemented by your subclass.
        n (int).
        m (int).
        i (int).
        val(double).
        
        for i=0, i < z, i++:{
            n = random[neuronCount - 1].
            m = random[neuronCount - 1].
            val = random[2.0]- 1.0.
            if m != n:{
                weights set-value to val at-x n at-y m.
            }
        }
    + to mutate-meta-connections connects z(int):
        % Implement this method to mutate the genes of this object.  This method
        % must be implemented by your subclass.
        n (int).
        m (int).
        i (int).
        val(double).
        
        for i=0, i < z, i++:{
            n = random[meta-neuronCount - 1].
            m = random[meta-neuronCount - 1].
            val = random[2.0]- 1.0.
            if m != n:{
                meta-weights set-value to val at-x n at-y m.
            }
        }
    + to randomize:
        % Implement this method to randomize the genes of this object.  This method
        % must be implemented by your subclass.
        n (int).
        #val(double).
        
        self init-random-structure with-connectivity-percent 0.5  with-autapses 0.
        self randomize-weights between -1.0
                           and 1.0
                           with-autapses 0.
        #die "The method \"randomize\" must be implemented in your GeneticAlgorithmIndividual subclass!".
     + to randomize-meta:
        % Implement this method to randomize the genes of this object.  This method
        % must be implemented by your subclass.
        n (int).
        #val(double).
        
        self init-random-meta-structure with-connectivity-percent 0.5  with-autapses 0.
        self randomize-meta-weights between -1.0
                           and 1.0
                           with-autapses 0.
                           
    + to crossover-two-point from-parent-1 parent1 (object) from-parent-2 parent2 (object):
        % Implement this method to make this object become a crossover of parent1 
        % and parent2.  This method must be implemented by your subclass if 
        % crossover is enabled.
        
        # Make 2 point crossover
        # Ok here it is
        n (int).
        m (int).
        o (int).
        p (int).
        #q (int).
        r (int).
        i (int).
        val(double).
        newhomeland (string).
        n = random [neuronCount - 1].
        m = random [neuronCount - 1].
        o = random [neuronCount - 1 - n].
        o = o + n.
        p = random [neuronCount - 1].
        print "crossover point 1 $n - $m : point 2 $o - $p".
        for i=0, i < neuronCount, i++:{
            for r=0, r < neuronCount, r++:{
                if i!=r:{
                    if (i > n && i < o && r > m && r < p):{
                        val = parent1 get-weight at-x i at-y r.
                        #connections set-value to 1.0 at-x i at-y r.
                        weights set-value to val at-x i at-y r.
                        #print "parent 1 $i $r".
                    }
                    else:{
                        val = parent2 get-weight at-x i at-y r.
                        #connections set-value to 1.0 at-x i at-y r.
                        weights set-value to val at-x i at-y r.
                        #print "parent 2 2 2".
                    }
                }
            }
        }
        #homeland = 
        #newhomeland = (parent1 get-homeland).
        #newhomeland = "($newhomeland X $homeland)".
        #homeland = newhomeland.
        #die "The method \"crossover\" must be implemented in your GeneticAlgorithmIndividual subclass!". 
    + to crossover-omni-point from-parent-1 parent1 (object) from-parent-2 parent2 (object):
        % Implement this method to make this object become a crossover of parent1 
        % and parent2.  This method must be implemented by your subclass if 
        % crossover is enabled.
        n (int).
        m (int).
        o (int).
        p (int).
        #q (int).
        r (int).
        i (int).
        val(double).
        newhomeland (string).
        for i=0, i < neuronCount, i++:{
            for r=0, r < neuronCount, r++:{
                if i!=r:{
                    if random[2.0]>1:{
                        val = parent1 get-weight at-x i at-y r.
                        #connections set-value to 1.0 at-x i at-y r.
                        weights set-value to val at-x i at-y r.
                        #print "parent 1 $i $r".
                    }
                    else:{
                        val = parent2 get-weight at-x i at-y r.
                        #connections set-value to 1.0 at-x i at-y r.
                        weights set-value to val at-x i at-y r.
                        #print "parent 2 2 2".
                    }
                }
            }
        }
 
        #homeland = 
        #newhomeland = (parent1 get-homeland).
        #newhomeland = "($newhomeland X $homeland)".
        #homeland = newhomeland.
        #die "The method \"crossover\" must be implemented in your GeneticAlgorithmIndividual subclass!".         
    + to crossover-meta-two-point from-parent-1 parent1 (object) from-parent-2 parent2 (object):
        % Implement this method to make this object become a crossover of parent1 
        % and parent2.  This method must be implemented by your subclass if 
        % crossover is enabled.
        
        # Make 2 point crossover
        # Ok here it is
        n (int).
        m (int).
        o (int).
        p (int).
        #q (int).
        r (int).
        i (int).
        val(double).
        newhomeland (string).
        n = random [meta-neuronCount - 1].
        m = random [meta-neuronCount - 1].
        o = random [meta-neuronCount - 1 - n].
        o = o + n.
        p = random [neuronCount - 1].
        print "crossover point 1 $n - $m : point 2 $o - $p".
        for i=0, i < meta-neuronCount, i++:{
            for r=0, r < meta-neuronCount, r++:{
                if i!=r:{
                    if (i > n && i < o && r > m && r < p):{
                        val = parent1 get-meta-weight at-x i at-y r.
                        #meta-connections set-value to 1.0 at-x i at-y r.
                        meta-weights set-value to val at-x i at-y r.
                        #print "parent 1 $i $r".
                    }
                    else{
                        val = parent2 get-meta-weight at-x i at-y r.
                        #meta-connections set-value to 1.0 at-x i at-y r.
                        meta-weights set-value to val at-x i at-y r.
                        #print "parent 2 2 2".
                    }
                }
            }
        } 
    + to crossover-meta-omni-point from-parent-1 parent1 (object) from-parent-2 parent2 (object):
        % Implement this method to make this object become a crossover of parent1 
        % and parent2.  This method must be implemented by your subclass if 
        % crossover is enabled.

        r (int).
        i (int).
        val(double).
        for i=0, i < meta-neuronCount, i++:{
            for r=0, r < meta-neuronCount, r++:{
                if i!=r:{
                    if random[2.0]>1:{
                        val = parent1 get-meta-weight at-x i at-y r.
                        #meta-connections set-value to 1.0 at-x i at-y r.
                        meta-weights set-value to val at-x i at-y r.
                        #print "parent 1 $i $r".
                    }
                    else{
                        val = parent2 get-meta-weight at-x i at-y r.
                        #meta-connections set-value to 1.0 at-x i at-y r.
                        meta-weights set-value to val at-x i at-y r.
                        #print "parent 2 2 2".
                    }
                }
            }
        }  

  + to get-copy:
  	#XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXxxthis needs updated
        #n (int).
        m (int).
        i (int).
        val(double).
        rtn (object).
         
        rtn = new NeuralNetwork4.
        rtn init-with neuron-count neuronCount.
        for i=0, i<neuronCount, i++:{
            for m=0, m<neuronCount, m++:{
                if i!=m:{
                    val = self get-weight at-x i at-y m.
                    if val != 0 :{
                        rtn set-connection-weight-matrix to val at-x i at-y m.
                    }
                }
            }
        }
        for i=0, i < meta-neuronCount, i++:{
            for m=0, m< meta-neuronCount, m++:{
                if i!=m:{
                    val = self get-meta-weight at-x i at-y m.
                    if val != 0 :{
                        rtn set-meta-connection-weight-matrix to val at-x i at-y m.
                    }
                }
            }
        }        
        rtn set-homeland of homeland.
        return rtn.
    + to make-new-pointer-for size theNetworkSize(int):
        network = neuralNetworkNew(theNetworkSize).
        return self.
    + to set-homeland of h (string):
        homeland = h.
    + to get-homeland:
        return homeland.
    + to re-states:
            n(int).
            for n = 0, n < neuronCount, n++:{
                neuralNetworkSetNeuronState(network, n, 0.0).
            }
    + to decay-by ratio val(double):
            n(int).
            tmp(double).
            for n = 0, n < neuronCount, n++:{
                tmp = neuralNetworkGetNeuronState(network, n).
                tmp = tmp * val.
                neuralNetworkSetNeuronState(network, n, tmp).
            }
    + to re-meta-states:
            n(int).
            for n = 0, n < meta-neuronCount, n++:{
                neuralNetworkSetNeuronState(meta-network, n, 0.0).
            }
    + to decay-meta-by ratio val(double):
            n(int).
            tmp(double).
            for n = 0, n < meta-neuronCount, n++:{
                tmp = neuralNetworkGetNeuronState(meta-network, n).
                tmp = tmp * val.
                neuralNetworkSetNeuronState(meta-network, n, tmp).
            }            
    + to set-fitness to fit(double):
            fitness = fit.
    + to get-fitness:
            return fitness.
    + to get-rentA:
    		print "$parentAfitness".
    	    return parentAfitness.
    + to get-rentB:
    	    return parentBfitness.
    + to set-parentA to rent(double):
    		parentAfitness = rent.
    + to set-parentB to rent(double):
    		parentBfitness = rent.    		
}
Genome : NeuralGenome2 [version 2.4] {
    + variables:
        weights (list).                 #serialization of the weight matrix
        size (int).                     #I think all weight matrices are square
        homeland(string).
        meta-weights (list).
        meta-size (int).
        parentA(double).
        parentB(double).
        fitness(double).
        
    + to set-weights of-matrix mat (object) of-size sz (int) :
            i(int).
            j(int).
            count (int).
            val (double).
            count = 0.
            for i = 0, i < sz, i++:{
                for j = 0, j < sz, j++:{
                    val = mat get-value at-x j at-y i.                  #row by row XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                    push val onto weights.
                    #weights [ count++ ] = val.
                }
            }
            size = sz.
    + to set-meta-weights of-matrix mat (object) of-size sz (int) :
            i(int).
            j(int).
            count (int).
            val (double).
            count = 0.
            for i = 0, i < sz, i++:{
                for j = 0, j < sz, j++:{
                    val = mat get-value at-x j at-y i.                  #row by row XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                    push val onto meta-weights.
                    #weights [ count++ ] = val.
                }
            }
            meta-size = sz.            
    + to compare gene g(object):
            dif(double).
            val1(double).
            val2(double).
            i(int).
            j(int).
            k(int).
            k = |weights|.
            print"comparing gene $k".
            for i = 0, i < size, i++:{
                for j = 0, j < size, j++:{
                    val1 = g get-val at-x j at-y i.                  #row by row XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                    val2 = self get-val at-x j at-y i.
                    dif += |(val1 - val2)|.
                }
            }
            if (meta-size > 0):{
            	for i = 0, i < meta-size, i++:{
                	for j = 0, j < meta-size, j++:{
                    		val1 = g get-meta-val at-x j at-y i.                  #row by row XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                    		val2 = self get-meta-val at-x j at-y i.
                    		dif += |(val1 - val2)|.
                	}
                }
            }            
            return dif.
            
    + to get-val at-x x (int) at-y y (int):
            val (double).
            i (int).
            i = (y * size) + (x).
            val = weights{i}.
            return val.
    + to get-meta-val at-x x (int) at-y y (int):
            val (double).
            i (int).
            i = (y * meta-size) + (x).
            val = meta-weights{i}.
            return val.
            
    + to get-size:
            return size.
            
    + to get-meta-size:
    	    return meta-size.
    	    
    + to set-homeland of h(string):
            homeland = h.
    + to get-homeland:
            return homeland.
    + to get-fitness:
    	    return fitness.
    + to get-parentA:
    	    return parentA.
    + to get-parentB:
    	    return parentB.
    + to set-fitness to fit(double):
    	    fitness = fit.
    + to set-parentA to rent(double):
    		parentA = rent.
    + to set-parentB to rent(double):
    		parentB = rent.   
    + to save-as-text named fileName(string):
	    f(object).
	    record(double).
	    f = new File.
	    f open-for-writing with-file fileName.
	    f write text "$homeland\n".
	    if UTIL2:{
	    	f write text "$parentA\n".
	    	f write text "$parentB\n".
	    	f write text "$fitness\n".
	    }
	    f write text "$size\n".
	    f write text "$meta-size\n". 
	    foreach record in weights:{
		f write text "$record\n".
	    }
	    #f write text "\n".
	    foreach record in meta-weights:{
		f write text "$record\n".
	    }
	    #f write text "\n"
	    f close.
     + to load-from-text named fileName(string):
	    f(object).
	    record(string).
	    caster(double).
	    trip(int).
	    step(int).
	    stat(int).
	    trip = 0.
	    step = 0.
	    stat = 0.
	    #record{0} = 0.
	    f = new File.
	    f open-for-reading with-file fileName.
	    while (trip != 5):{ #
			record = (f read-line).
			if (trip == 4):{
				if (step < (meta-size * meta-size)):{
					caster = record.
					#push caster onto meta-weights.
					meta-weights{step}=caster.
					step+=1.
					#print"$record meta $step $caster".					
				} else {
					#print "$meta-weights".
					trip += 1.
				}
			}			
			if (trip == 3):{
				#print "size in load $size".
				if (step < (size * size)):{
					caster = record.
					#push caster onto weights.
					weights{step} = caster.
					step += 1.
					#print"$record weights $step $caster".					
					
				} else {
					trip += 1.
					step = 0.
					#print"$weights".
				}
			}			
			if (trip == 2):{
				meta-size = record.	
				trip += 1.
			}
			if (trip == 1):{
				size = record.
				while (size != "50"):{
					record = (f read-line).
					size = record.
				}				
				#size -= 1.
				trip += 1.
				print"size $size".
			}
			if (trip == 0):{
				if UTIL:{
					if stat == 3:{
						fitness = record.
						trip += 1.
					}
					if stat == 2:{
						parentB = record.
						stat += 1.
					}
					if stat == 1:{ 
						parentA = record.
						stat += 1.
					}
				}
				if stat == 0:{
					homeland = record.
					stat += 1.
					if !(UTIL):{
						trip += 1.
					}
				}
				print"homeland $homeland".
			}
	    }
		print"Made it through load".
    	    f close.
}
NeuralNetwork4 : RecurrentNetwork2 [version 2.3] {

    + to update-state:
    % updates the network's state based on current state and
    % inputs
        neuralRecurrentUpdateState(network).

    
}

NeuralNetwork4 : FeedForwardNetwork2 [version 2.3] {


}

Mobile : NeuronImage2 [version 2.3] {

    + variables:
        texture (object).
        neurons (object).
        myShape (object).
        
    + to init-with nodes theVector (object) 
                   color theColor = "Green" (string)
                   shape-scale shapeScale = 1 (int)
                   value-scale valueScale = 1.0 (float):
    
        neurons = theVector.
        texture = ((new VectorImage) init-with the-vector neurons scale valueScale).
        myShape = ((new Cube) init-with size ((shapeScale * ((neurons get-dimension) / 10.0)), (shapeScale * (neurons get-dimension)), 1)).
        self set-shape to myShape.
        self set-texture-image to texture.
        self set-texture-scale to (((neurons get-dimension) * shapeScale)).
        
        if theColor == "Red":
            texture set-red to neurons.
        else: if theColor == "Green":
            texture set-green to neurons.
        else: if theColor == "Blue":
            texture set-blue to neurons.
        else: print "Please use 'Green,' 'Red' or 'Blue' for NodeImage.".
        
        self add-menu named "Print Activity" for-method "print-neuron-activity".
        
        return self.

    + to destroy:
        free(texture).
        free(myShape).
        free(neurons).
        super destroy.
        
    + to update-display:
        texture iterate.
        
    + to print-neuron-activity:
        neurons print-matlab-style.
}

Mobile : WeightImage2 [version 2.3] {

    + variables:
        texture (object).
        weights (object).
        weightColor (string).
        weightToggle (int).
        connections (object).
        connectionColor (string).
        connectionToggle (int).

    + to init:
        weightToggle = 0.
        connectionToggle = 0.
        
    + to destroy:
        free(texture).
        free(weights).
        free(connections).
        super destroy.
        
    + to init-with weights theWeights (object)
                   connections theConnections (object) 
                   weight-color theWeightColor = "Blue" (string)
                   connection-color theConnectionColor = "Red" (string)
                   shape-scale shapeScale = 1.0 (float)
                   value-scale valueScale = 1.0 (float):
    
        weights = theWeights.
        weightColor = theWeightColor.
        connections = theConnections.
        connectionColor = theConnectionColor.
        
        texture = ((new MatrixImage) init-with the-matrix weights scale valueScale).
        
        self set-shape to ((new Cube) init-with size ((shapeScale * (weights get-x-dimension)), (shapeScale * (weights get-y-dimension)), 1)).
        self set-texture-image to texture.
        self set-texture-scale to (((weights get-x-dimension) * shapeScale)).
    
        self toggle-weights.
                
        self add-menu named "Print Weights" for-method "print-weights".
        self add-menu named "Toggle Weight Display" for-method "toggle-weights".
        self add-menu named "Print Connections" for-method "print-connections".
        self add-menu named "Toggle Connection Display" for-method "toggle-connections".
        
        return self.
        
    + to update-display:
        texture iterate.

    - to switch-display on-color theColor (string) to theObject (object):
            
        if theColor == "Red":
            texture set-red to theObject.
        else: if theColor == "Green":
            texture set-green to theObject.
        else: if theColor == "Blue":
            texture set-blue to theObject.
        else: print "Please use 'Green,' 'Red' or 'Blue' for WeightImage.".


    + to toggle-weights:
        if weightToggle:
        {
            self switch-display on-color weightColor to 0.
            weightToggle = 0.
        }
        else:
        {
            self switch-display on-color weightColor to weights.
            weightToggle = 1.
        }
            
    + to toggle-connections:
        if connectionToggle:
        {
            self switch-display on-color connectionColor to 0.
            connectionToggle = 0.
        }
        else:
        {
            self switch-display on-color connectionColor to connections.
            connectionToggle = 1.
        }
                
    + to print-weights:
        weights print-matlab-style.
        
    + to print-connections:
        connections print-matlab-style.
                   
}