def pet(memory, hidden_dim, order, learning_rate, mark='pet'):
# Initiate a predictor
model = NeuralNet(memory_depth=memory, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([memory]))
nn.add(Linear(output_dim=hidden_dim, use_bias=False))
nn.add(inter_type=pedia.sum)
for i in range(1, order + 1):
nn.add_to_last_net(Homogeneous(order=i))
# Build model
model.default_build(learning_rate=learning_rate)
return model
def rnn0(th):
assert isinstance(th, NlsHub)
# Initiate a neural net model
nn_class = lambda mark: Predictor(mark=mark, net_type=Recurrent)
model = NeuralNet(th.memory_depth, mark=th.mark, nn_class=nn_class)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input(sample_shape=[th.memory_depth]))
for _ in range(th.num_blocks):
nn.add(BasicRNNCell(state_size=th.hidden_dim))
nn.add(Linear(output_dim=1))
# Build
model.default_build(th.learning_rate)
return model
def tlp(memory_depth, hidden_dim, mark='tlp'):
# Hyper-parameters
learning_rate = 0.001
# Initiate a predictor
model = NeuralNet(memory_depth, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([memory_depth]))
nn.add(Linear(output_dim=hidden_dim))
nn.add(Activation('sigmoid'))
nn.add(Linear(output_dim=1, use_bias=False))
# Build model
model.default_build(learning_rate=learning_rate)
return model
def mlp_01(mark, memory_depth, layer_dim, learning_rate, activation='relu'):
# Configurations
pass
# Initiate a predictor
model = NeuralNet(memory_depth, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([memory_depth]))
nn.add(Linear(output_dim=layer_dim))
nn.add(Activation(activation))
nn.add(Linear(output_dim=1))
# Build model
model.default_build(learning_rate)
# Return model
return model
def svn(memory_depth, order, hidden_dim, mark='svn'):
# Hyper-parameters
learning_rate = 0.001
# Initiate a predictor
model = NeuralNet(memory_depth, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([memory_depth]))
nn.add(Linear(output_dim=hidden_dim))
nn.add(Polynomial(order=order))
nn.add(Linear(output_dim=1, use_bias=False))
# Build model
# optimizer = tf.train.GradientDescentOptimizer(learning_rate)
optimizer = tf.train.AdamOptimizer(learning_rate)
model.default_build(optimizer=optimizer, learning_rate=learning_rate)
return model
def mlp_00(th):
assert isinstance(th, NlsHub)
# Initiate a predictor
model = NeuralNet(th.memory_depth, mark=th.mark, nn_class=Predictor)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([th.memory_depth]))
for i in range(th.num_blocks):
nn.add(
Linear(output_dim=th.hidden_dim,
weight_regularizer=th.regularizer,
strength=th.reg_strength))
nn.add(Activation(th.actype1))
nn.add(Linear(output_dim=1))
# Build model
model.default_build(th.learning_rate)
# Return model
return model
def bres_net_wid0(th, activation='relu'):
assert isinstance(th, NlsHub)
# Initiate a neural net model
th.mark = '{}-{}'.format(th.mark, 'wid')
model = NeuralNet(th.memory_depth, mark=th.mark, nn_class=BResNet)
nn = model.nn
assert isinstance(nn, BResNet)
# Add layers
nn.add(Input([th.memory_depth]))
nn._inter_type = pedia.fork
for _ in range(th.num_blocks):
branch = nn.add()
branch.add(Linear(output_dim=th.hidden_dim))
branch.add(Activation(activation))
branch.add(Linear(output_dim=1))
# Build
model.default_build(th.learning_rate)
# Return model
return model
def bres_net_dep0(th, activation='relu'):
assert isinstance(th, NlsHub)
# Initiate a neural net model
th.mark = '{}-{}'.format(th.mark, 'dep')
model = NeuralNet(th.memory_depth, mark=th.mark, nn_class=BResNet)
nn = model.nn
assert isinstance(nn, BResNet)
# Add layers
nn.add(Input([th.memory_depth]))
for _ in range(th.num_blocks):
nn.add(
Linear(output_dim=th.hidden_dim,
weight_regularizer=th.regularizer,
strength=th.reg_strength))
nn.add(Activation(activation))
branch = nn.add_branch()
branch.add(Linear(output_dim=1))
# Build
model.default_build(th.learning_rate)
# Return model
return model
def net_00(memory_depth, learning_rate=0.001):
# Configuration
hidden_dim = 10
homo_order = 4
mark = 'net_h{}_homo{}'.format(hidden_dim, homo_order)
# Initiate a predictor
model = NeuralNet(memory_depth, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([memory_depth]))
nn.add(Linear(output_dim=hidden_dim))
nn.add(inter_type=pedia.sum)
for i in range(1, homo_order + 1):
nn.add_to_last_net(Homogeneous(i))
# Build model
model.default_build(learning_rate)
# Return model
return model
def svn_00(memory, learning_rate=0.001):
# Configuration
D = memory
hidden_dims = [2 * D] * 3
p_order = 2
mark = 'svn_{}_{}'.format(hidden_dims, p_order)
# Initiate a predictor
model = NeuralNet(memory, mark=mark)
nn = model.nn
assert isinstance(nn, Predictor)
# Add layers
nn.add(Input([D]))
for dim in hidden_dims:
nn.add(Linear(output_dim=dim))
nn.add(Polynomial(p_order))
nn.add(Linear(output_dim=1))
# Build model
model.default_build(learning_rate)
return model
def mlp02(mark,
memory_depth,
layer_num,
hidden_dim,
learning_rate,
activation,
identity_init=True):
# Initiate a neural net
if identity_init:
model = NeuralNet(memory_depth,
mark=mark,
bamboo=True,
identity_initial=True)
else:
model = NeuralNet(memory_depth, mark=mark, bamboo=True)
nn = model.nn
assert isinstance(nn, Bamboo)
# Add layers
nn.add(Input([memory_depth]))
for _ in range(layer_num):
nn.add(Linear(output_dim=hidden_dim))
nn.add(Activation(activation))
branch = nn.add_branch()
branch.add(Linear(output_dim=1))
nn.add(Linear(output_dim=hidden_dim))
nn.add(Activation(activation))
nn.add(Linear(output_dim=1))
# Build model
model.default_build(learning_rate)
# Return model
return model
