def test_backpropagation(self):
output = StepOutputLayer(1, output_bounds=(-1, 1))
weight1 = np.array([
[0.31319847, -1.17858149, 0.71556407],
[1.60798015, 0.16304449, -0.22483005],
[-0.90144173, 0.58500625, -0.01724167]
])
weight2 = np.array([
[-1.34351428],
[0.45506056],
[0.24790366],
[-0.74360389]
])
input_layer = TanhLayer(2, weight=weight1)
hidden_layer = TanhLayer(3, weight=weight2)
network = Backpropagation(
(input_layer > hidden_layer > output),
step=0.3,
verbose=False
)
network.train(xor_input_train, xor_target_train, epochs=1000)
self.assertEqual(round(network.last_error_in(), 2), 0)
def test_handle_errors(self):
data, target = datasets.make_classification(300, n_features=4,
n_classes=2)
x_train, x_test, y_train, y_test = cross_validation.train_test_split(
data, target, train_size=0.7
)
with self.assertRaises(ValueError):
# First network has two output layers and the second
# just one.
ensemble.DynamicallyAveragedNetwork([
algorithms.RPROP((4, 10, 2), step=0.1),
algorithms.Backpropagation((4, 10, 1), step=0.1)
])
with self.assertRaises(ValueError):
# Use ensemble with less than one network
ensemble.DynamicallyAveragedNetwork([
algorithms.Backpropagation((4, 10, 1), step=0.1)
])
with self.assertRaises(ValueError):
# Output between -1 and 1
dan = ensemble.DynamicallyAveragedNetwork([
algorithms.Backpropagation(
SigmoidLayer(4) > TanhLayer(10) > OutputLayer(1),
step=0.01
),
algorithms.RPROP((4, 10, 1), step=0.1)
])
dan.train(x_train, y_train, epochs=10)
dan.predict(x_test)
def test_backpropagation(self):
weight1 = np.array([[-0.53980522, -0.64724144, -0.92496063],
[-0.04144865, -0.60458235, 0.25735483],
[0.08818209, -0.10212516, -1.46030816]])
weight2 = np.array([[0.54230442], [0.1393251], [1.59479241],
[0.1479949]])
input_layer = TanhLayer(2, weight=weight1)
hidden_layer = TanhLayer(3, weight=weight2)
output = StepOutputLayer(1, output_bounds=(-1, 1))
network = Backpropagation(input_layer > hidden_layer > output,
step=0.3,
decay_rate=0.0001,
optimizations=[WeightDecay])
network.train(xor_input_train, xor_target_train, epochs=500)
self.assertEqual(round(network.last_error_in(), 2), 0)
def test_backpropagation(self):
weight1 = np.array([[0.22667075, 0.38116981, 0.62686969],
[1.13062085, 0.40836474, -0.50492125],
[-0.22645265, 1.13541005, -2.7876409]])
weight2 = np.array([[0.63547163], [0.63347214], [-1.3669957],
[-0.42770718]])
input_layer = TanhLayer(2, weight=weight1)
hidden_layer = TanhLayer(3, weight=weight2)
output = StepOutputLayer(1, output_bounds=(-1, 1))
network = Backpropagation(input_layer > hidden_layer > output,
step=0.3,
zero_weight=20,
optimizations=[WeightElimination])
network.train(xor_input_train, xor_target_train, epochs=350)
self.assertEqual(round(network.last_error_in(), 2), 0)
def setUp(self):
super(LearningRateUpdatesTestCase, self).setUp()
self.first_step = 0.3
# Weights
self.weight1 = np.array([
[0.57030714, 0.64724479, 0.74482306],
[0.12310346, 0.26571213, 0.74472318],
[0.5642351, 0.52127089, 0.57070108],
])
self.weight2 = np.array([
[0.2343891],
[0.70945912],
[0.46677056],
[0.83986252],
])
# Layers
input_layer = TanhLayer(2, weight=self.weight1)
hidden_layer = TanhLayer(3, weight=self.weight2)
output = StepOutputLayer(1, output_bounds=(-1, 1))
self.connection = input_layer > hidden_layer > output
def test_backpropagation(self):
weight1 = np.array([[-0.53980522, -0.64724144, -0.92496063],
[-0.04144865, -0.60458235, 0.25735483],
[0.08818209, -0.10212516, -1.46030816]])
weight2 = np.array([[0.54230442], [0.1393251], [1.59479241],
[0.1479949]])
input_layer = TanhLayer(2, weight=weight1)
hidden_layer = TanhLayer(3, weight=weight2)
output = StepOutputLayer(1, output_bounds=(-1, 1))
network2 = Momentum(
(input_layer > hidden_layer > output),
step=0.1,
momentum=0.1,
use_raw_predict_at_error=True,
)
network2.train(xor_input_train, xor_target_train, epochs=300)
self.assertEqual(round(network2.last_error_in(), 2), 0)
def setUp(self):
super(GradientDescentTestCase, self).setUp()
output = StepOutputLayer(1, output_bounds=(-1, 1))
self.connection = TanhLayer(2) > TanhLayer(5) > output