# Architecture parameters
number_hidden_units = 20
b1 = NormalVariable(np.zeros((number_hidden_units, 1)), 10 * np.ones(
(number_hidden_units, 1)), "b1")
b2 = NormalVariable(np.zeros((number_output_classes, 1)), 10 * np.ones(
(number_output_classes, 1)), "b2")
weights1 = NormalVariable(np.zeros(
(number_hidden_units, number_pixels)), 10 * np.ones(
(number_hidden_units, number_pixels)), "weights1")
weights2 = NormalVariable(
np.zeros((number_output_classes, number_hidden_units)), 10 * np.ones(
(number_output_classes, number_hidden_units)), "weights2")
# Forward pass
hidden_units = BF.tanh(BF.matmul(weights1, x) + b1)
final_activations = BF.matmul(weights2, hidden_units) + b2
k = CategoricalVariable(softmax_p=final_activations, name="k")
# Probabilistic model
model = ProbabilisticModel([k])
# Observations
k.observe(labels)
# Variational Model
Qb1 = NormalVariable(np.zeros((number_hidden_units, 1)),
0.2 * np.ones((number_hidden_units, 1)),
"b1",
learnable=True)
Qb2 = NormalVariable(np.zeros((number_output_classes, 1)),
imagesGT = []
imagesNoise = []
images1 = []
images2 = []
images3 = []
for rep in range(N_rep):
h_size = 120
W1 = DeterministicVariable(np.random.normal(0., 0.2, (h_size, h_size)),
"W1",
learnable=False)
W2 = DeterministicVariable(np.random.normal(0., 0.2, (h_size, h_size)),
"W2",
learnable=False)
#V = DeterministicVariable(np.random.normal(0., 1., (100, h_size)), "V", learnable=False)
f = lambda z, W: z + BF.tanh(BF.matmul(W, z))
F = lambda z, W1, W2: f(f(z, W1), W2)
measurement_noise = 2. #1.5
z = [
NormalVariable(np.zeros((h_size, 1)),
np.ones((h_size, 1)),
"z0",
learnable=False)
]
img = [
DeterministicVariable(decoder(BF.reshape(z[0], (h_size, 1, 1))),
"img0",
learnable=False)
]
x = [
labels = EmpiricalVariable(output_labels,
indices=minibatch_indices,
name="labels",
is_observed=True)
# Architecture parameters
weights1 = NormalVariable(
np.zeros((number_hidden_nodes, number_regressors)), 10 * np.ones(
(number_hidden_nodes, number_regressors)), "weights1")
weights2 = NormalVariable(
np.zeros((number_output_classes, number_hidden_nodes)),
10 * np.ones(
(number_output_classes, number_hidden_nodes)), "weights2")
# Forward pass
final_activations = BF.matmul(weights2, BF.tanh(BF.matmul(weights1,
x)))
k = CategoricalVariable(softmax_p=final_activations, name="k")
# Probabilistic model
model = ProbabilisticModel([k])
# Observations
k.observe(labels)
# Variational model
num_particles = N
initial_locations1 = [
np.random.normal(0., 1., (number_hidden_nodes, number_regressors))
for _ in range(num_particles)
]
initial_locations2 = [
from brancher.standard_variables import NormalVariable, LogNormalVariable, LogitNormalVariable
from brancher import inference
import brancher.functions as BF
# Probabilistic model #
T = 100
nu = LogNormalVariable(0.3, 1., 'nu')
x0 = NormalVariable(0., 1., 'x0')
b = LogitNormalVariable(0.5, 1.5, 'b')
x = [x0]
names = ["x0"]
for t in range(1, T):
names.append("x{}".format(t))
x.append(NormalVariable(BF.tanh(b * x[t - 1]), nu, names[t]))
AR_model = ProbabilisticModel(x)
# Generate data #
data = AR_model._get_sample(number_samples=1)
time_series = [float(data[xt].data) for xt in x]
true_b = data[b].data
true_nu = data[nu].data
print("The true coefficient is: {}".format(float(true_b)))
# Observe data #
[xt.observe(data[xt][:, 0, :]) for xt in x]
# Variational distribution #
Qnu = LogNormalVariable(0.5, 1., "nu", learnable=True)
Qb = LogitNormalVariable(0.5, 0.5, "b", learnable=True)