def initializeNN(self):
for i in range(0, self.noInput):
w = []
wb = []
if len(self.inputWeights) != 0 and len(self.inputBiasWeights) != 0:
w = [self.inputWeights[i]]
wb = self.inputBiasWeights[i]
self.input[i] = (Neuron.Neuron(af.NoActivationFunction(), 1, w,
wb))
for i in range(0, self.noHiddenLayers):
layer = [None] * self.noHidden
for j in range(0, self.noHidden):
# Find weights for current neuron
w = []
wb = []
if len(self.hiddenWeights) != 0 and len(
self.hiddenBiasWeights) != 0:
if i == 0:
w = self.hiddenWeights[:self.noInput]
else:
start = self.noInput + (i - 1) * self.noHidden
end = self.noInput + i * self.noHidden
w = self.hiddenWeights[start:end]
wb = self.hiddenBiasWeights[i * self.noHidden + j]
else:
# No weights present => initialise random neuron
pass
# Add new neuron
if i == 0:
layer[j] = (Neuron.Neuron(af.Logistic(), self.noInput, w,
wb))
else:
layer[j] = (Neuron.Neuron(af.Logistic(), self.noHidden, w,
wb))
self.hidden[i] = layer
for i in range(0, self.noOutput):
w = []
wb = []
if len(self.outputWeights) != 0 and len(
self.outputBiasWeights) != 0:
w = self.outputWeights[i * self.noHidden:(i + 1) *
self.noHidden]
wb = self.outputBiasWeights[i]
self.output[i] = (Neuron.Neuron(af.Logistic(), self.noHidden, w,
wb))
def initializeNN(self):
for i in range(0, self.noInput):
w = None
wb = None
if self.inputWeights != None and self.inputBiasWeights != None:
w = [self.inputWeights[i]]
wb = self.inputBiasWeights[i]
# self.input.append(Neuron(af.NoActivationFunction(), self.noInput))
self.input.append(Neuron(af.NoActivationFunction(), 1, w, wb))
for i in range(0, self.noHiddenLayers):
layer = []
for j in range(0, self.noHidden):
# Find weights for current neuron
w = None
wb = None
if self.hiddenWeights != None and self.hiddenBiasWeights != None:
if i == 0:
w = self.hiddenWeights[:self.noInput]
wb = self.hiddenBiasWeights[j]
else:
w = self.hiddenWeights[self.noInput + (i - 1) *
self.noHidden:self.noInput +
i * self.noHidden]
wb = self.hiddenBiasWeights[i * self.noHidden + j]
else:
# No weights present => initialise random neuron
pass
# Append new neuron
if i == 0:
layer.append(Neuron(af.Logistic(), self.noInput, w, wb))
else:
layer.append(Neuron(af.Logistic(), self.noHidden, w, wb))
self.hidden.append(layer)
for i in range(0, self.noOutput):
w = None
wb = None
if self.outputWeights != None and self.outputBiasWeights != None:
w = self.outputWeights
wb = self.outputBiasWeights[i]
self.output.append(Neuron(af.Logistic(), self.noHidden, w, wb))
def testScaledExponentialLinear(self, x, y):
self.assertAlmostEqual(
ActivationFunctions.scaledExponentialLinear(x), y, 2)
def testLeakyRectifiedLinear(self, x, y):
self.assertEqual(ActivationFunctions.leakyRectifiedLinear(x), y)
def testParametricRectifiedLinear(self, x, y):
self.assertEqual(ActivationFunctions.parametricRectifiedLinear(x), y)
def testInverseSquareRoot(self, x, y):
self.assertAlmostEqual(ActivationFunctions.inverseSquareRoot(x), y, 2)
def testBipolarRectifiedLinear(self, x, y):
self.assertEqual(ActivationFunctions.bipolarRectifiedLinear(x), y)
def testArcSinH(self, x, y):
self.assertAlmostEqual(ActivationFunctions.arcSinH(x), y, 2)
def testElliotSig(self, x, y):
self.assertAlmostEqual(ActivationFunctions.elliotSig(x), y, 2)
def testSQNL(self, x, y):
self.assertEqual(ActivationFunctions.sqnl(x), y)
def testTanh(self, x, y):
self.assertAlmostEqual(ActivationFunctions.tanH(x), y, 2)
def testSigmoid(self, x, y):
self.assertAlmostEqual(ActivationFunctions.sigmoid(x), y, 2)
def testBinaryStep(self, x, y):
self.assertEqual(ActivationFunctions.binaryStep(x), y)
def testIdentity(self, x, y):
self.assertEqual(ActivationFunctions.identity(x), y)