def _gradient(self, weights, lambda_value):
thetas = list(reshape_vector(weights, self.theta_shapes))
activations = self._activations(thetas)
l = lambda_value
# sigmas = [sigma3, sigma2, ...]
sigmas = [activations[-1]-self.Y]
for ind,layer in enumerate(self.z[-2::-1]):
if self.add_bias:
layer = add_bias(layer)
sigma = np.dot(sigmas[-1], thetas[-1-ind])*sigmoid_gradient(layer)
sigmas.append(del_bias(sigma))
# deltas = [delta1, delta2, ...]
deltas = []
for activation, sigma in zip(activations, sigmas[::-1]):
deltas.append(np.dot(sigma.T, activation))
# gradients = [theta1_grad, theta2_grad, ...]
gradients = []
for theta, delta in zip(thetas, deltas):
theta = del_bias(theta)
theta = add_bias(theta, values_function=np.zeros)
gradient = delta/self.m + np.dot((l/self.m), theta)
gradients.append(gradient.T.ravel())
return np.concatenate(gradients)
def _gradient(self, weights, lambda_value):
thetas = list(reshape_vector(weights, self.theta_shapes))
activations = self._activations(thetas)
l = lambda_value
# sigmas = [sigma3, sigma2, ...]
sigmas = [activations[-1] - self.Y]
for ind, layer in enumerate(self.z[-2::-1]):
if self.add_bias:
layer = add_bias(layer)
sigma = np.dot(sigmas[-1],
thetas[-1 - ind]) * sigmoid_gradient(layer)
sigmas.append(del_bias(sigma))
# deltas = [delta1, delta2, ...]
deltas = []
for activation, sigma in zip(activations, sigmas[::-1]):
deltas.append(np.dot(sigma.T, activation))
# gradients = [theta1_grad, theta2_grad, ...]
gradients = []
for theta, delta in zip(thetas, deltas):
theta = del_bias(theta)
theta = add_bias(theta, values_function=np.zeros)
gradient = delta / self.m + np.dot((l / self.m), theta)
gradients.append(gradient.T.ravel())
return np.concatenate(gradients)
def predict(self, input_layer):
output_layer = input_layer
thetas = reshape_vector(self.weights, self.theta_shapes)
for theta in thetas:
if self.add_bias:
output_layer = np.append(1, output_layer)
output_layer = self.h(theta.dot(output_layer))
return output_layer
def predict(self, input_layer):
output_layer = input_layer
thetas = reshape_vector(self.weights, self.theta_shapes)
for theta in thetas:
if self.add_bias:
output_layer = np.append(1, output_layer)
output_layer = self.h(theta.dot(output_layer))
return output_layer
def _cost_function(self, weights, lambda_value):
thetas = list(reshape_vector(weights, self.theta_shapes))
activations = self._activations(thetas)
l = lambda_value
p = self._penalty(thetas)
h = activations[-1] # Output layer
r = (l*p)/(2*self.m)
cost = np.sum(np.sum(-self.Y*np.log(h) - (1-self.Y)*np.log(1-h), axis=1))/self.m + r
return cost
def _cost_function(self, weights, lambda_value):
thetas = list(reshape_vector(weights, self.theta_shapes))
activations = self._activations(thetas)
l = lambda_value
p = self._penalty(thetas)
h = activations[-1] # Output layer
r = (l * p) / (2 * self.m)
cost = np.sum(
np.sum(-self.Y * np.log(h) -
(1 - self.Y) * np.log(1 - h), axis=1)) / self.m + r
return cost
def test_reshape_vector(self):
vector, shapes = flatten_matrices(THETAS)
matrices = list(reshape_vector(vector, shapes))
for m, w in zip(matrices, THETAS):
self.assertTrue((m == w).all())
