added third experiment

code/network.py

@@ -697,8 +697,6 @@ if __name__ == '__main__':
                 exp.historical_particles[i] = net
                 K.clear_session()
     if False:
-        # this does not work as the aggregation function screws over the fixpoint computation....
-        # TODO: check for fixpoint in aggregated space...
         with FixpointExperiment() as exp:
             run_count = 1000
             net = TrainingNeuralNetworkDecorator(AggregatingNeuralNetwork(4, width=2, depth=2)).with_params(epsilon=0.1e-6)

code/setups/fixpoint-density.py

@@ -41,7 +41,7 @@ with Experiment('fixpoint-density') as exp:
         notable_nets = []
         for _ in tqdm(range(exp.trials)):
             net = net_generator().with_params(epsilon=exp.epsilon)
-            name = str(net.__class__.__name__) + " " + str(net.get_keras_params().get('activation'))
+            name = str(net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias='" + str(net.get_keras_params().get('use_bias')) + "'"
             count(counters, net, notable_nets)
         all_counters += [counters]
         all_notable_nets += [notable_nets]

code/setups/known-fixpoint-variation.py

@@ -9,13 +9,6 @@ from soup import prng
 
 from statistics import mean
 avg = mean
-
-def generate(e=0.0, f=0.0):
-    return [
-        np.array([[1.0+e, 0.0+f], [0.0+f, 0.0+f], [0.0+f, 0.0+f], [0.0+f, 0.0+f]], dtype=np.float32),
-        np.array([[1.0+e, 0.0+f], [0.0+f, 0.0+f]], dtype=np.float32),
-        np.array([[1.0+e], [0.0+f]], dtype=np.float32)
-    ]
     
 def generate_fixpoint_weights():
     return [

code/setups/training-fixpoints.py

@@ -0,0 +1,59 @@
+import sys
+
+sys.path += ['../', './']
+
+from util import *
+from experiment import *
+from network import *
+
+def generate_counters():
+    return {'divergent': 0, 'fix_zero': 0, 'fix_other': 0, 'fix_sec': 0, 'other': 0}
+
+def count(counters, net, notable_nets=[]):
+    if net.is_diverged():
+        counters['divergent'] += 1
+    elif net.is_fixpoint():
+        if net.is_zero():
+            counters['fix_zero'] += 1
+        else:
+            counters['fix_other'] += 1
+            notable_nets += [net]
+    elif net.is_fixpoint(2):
+        counters['fix_sec'] += 1
+        notable_nets += [net]
+    else:
+        counters['other'] += 1
+    return counters, notable_nets
+
+with Experiment('training_fixpoint') as exp:
+    exp.trials = 5
+    exp.run_count = 500
+    exp.epsilon = 1e-4
+    net_generators = []
+    for activation in ['linear', 'sigmoid', 'relu']:
+        for use_bias in [False]:
+            net_generators += [lambda activation=activation, use_bias=use_bias: WeightwiseNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+            net_generators += [lambda activation=activation, use_bias=use_bias: AggregatingNeuralNetwork(aggregates=4, width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+            net_generators += [lambda activation=activation, use_bias=use_bias: RecurrentNeuralNetwork(width=2, depth=2).with_keras_params(activation=activation, use_bias=use_bias)]
+    all_counters = []
+    all_notable_nets = []
+    all_names = []
+    for net_generator_id, net_generator in enumerate(net_generators):
+        counters = generate_counters()
+        notable_nets = []
+        for _ in tqdm(range(exp.trials)):
+            net = TrainingNeuralNetworkDecorator(net_generator()).with_params(epsilon=exp.epsilon)
+            name = str(net.net.__class__.__name__) + " activiation='" + str(net.get_keras_params().get('activation')) + "' use_bias=" + str(net.get_keras_params().get('use_bias'))
+            for run_id in range(exp.run_count):
+                loss = net.compiled().train(epoch=run_id+1)
+            count(counters, net, notable_nets)
+        all_counters += [counters]
+        all_notable_nets += [notable_nets]
+        all_names += [name]
+    exp.save(all_counters=all_counters)
+    exp.save(all_notable_nets=all_notable_nets)
+    exp.save(all_names=all_names)
+    for exp_id, counter in enumerate(all_counters):
+        exp.log(all_names[exp_id])
+        exp.log(all_counters[exp_id])
+        exp.log('\n')