Run and Training functions

Outlined run and training functions

Author: FinHerbig

and_net.py

@@ -71,6 +71,23 @@ def binary_to_spikes(self, val, nsteps=1000):
         return a_spikes
 
     # Runs the neural net
+    # Maybe include option to run without training neuron
     def run_net(self, input):
-        output = []
-        return output
+        # Initializes a current for the three input neurons
+        xIn = self.spikes_to_current(self.binary_to_spikes(input[0]), self.connections[0].weight)
+        yIn = self.spikes_to_current(self.binary_to_spikes(input[1]), self.connections[1].weight)
+        teachIn = self.spikes_to_current(self.binary_to_spikes(input[1] and input[0]), self.connections[2].weight)
+        self.neurons[0].sim(xIn, 1000)
+        self.neurons[1].sim(yIn, 1000)
+        self.neurons[2].sim(teachIn, 1000)
+        # Calculates the input current for the output by using an or function on all 3 spike outputs 
+        outIn = []
+        for i in range(1000):
+            outIn[i] = self.neurons[0].output[i] or self.neurons[1].output[i] or self.neurons[2].output[i]
+        self.neurons[3].sim(self.spikes_to_current(outIn, 1), 1000)
+        for i in range(1000):
+            output = output + self.neurons[3].output[i]
+        if output > 5:
+            return 1
+        else:
+            return 0

training.py

@@ -2,9 +2,9 @@
 net = and_net([], [])
 net.create_simple_net()
 # X at [0], Y at [1], Teacher at [2]
-net.connections[0].weight = .7
-net.connections[1].weight = .3
-net.connections[2].weight = .5
+net.connections[0].weight = 1
+net.connections[1].weight = 1
+net.connections[2].weight = 1
 # data[0] holds X, data[1] holds Y, output calculated by data[0][i] && data[1][i]
 data = [[]]
 lines = open(input("Enter Filepath: "), "r").readlines()
@@ -15,6 +15,17 @@
             data[j][i] = 0
         else:
             data[j][i] = 1
-#TODO does training and results and_net with proper weights
+# Trains the network
 for i in range(runs):
-    pass
+    #out = net.run_net([data[0][i], data[1][i], data[0][i] and data[1][i]])
+    #TODO Find better formula
+    for i in range(1000):
+        for j in range(2):
+            if net.neurons[j].output[i] == net.neurons[3].output[i] == 1:
+                #increase
+                net.connections[j].weight += .1
+            elif net.neurons[j].output[i] == 1 and net.neurons[3].output[i] == 0:
+                #decrease
+                net.connections[j].weight -= .1
+    for i in range(3):
+        net.neurons[i].clear