def __init__(self,
X_train,
y_train,
n_hidden,
n_epochs=40,
normalize=False):
"""
Constructor for the class implementing a Bayesian neural network
trained with the probabilistic back propagation method.
@param X_train Matrix with the features for the training data.
@param y_train Vector with the target variables for the
training data.
@param n_hidden Vector with the number of neurons for each
hidden layer.
@param n_epochs Numer of epochs for which to train the
network. The recommended value 40 should be
enough.
@param normalize Whether to normalize the input features. This
is recommended unles the input vector is for
example formed by binary features (a
fingerprint). In that case we do not recommend
to normalize the features.
"""
# We normalize the training data to have zero mean and unit standard
# deviation in the training set if necessary
if normalize:
self.std_X_train = np.std(X_train, 0)
self.std_X_train[self.std_X_train == 0] = 1
self.mean_X_train = np.mean(X_train, 0)
else:
self.std_X_train = np.ones(X_train.shape[1])
self.mean_X_train = np.zeros(X_train.shape[1])
X_train = (X_train - np.full(X_train.shape, self.mean_X_train)) / \
np.full(X_train.shape, self.std_X_train)
self.mean_y_train = np.mean(y_train)
self.std_y_train = np.std(y_train)
y_train_normalized = (y_train - self.mean_y_train) / self.std_y_train
# We construct the network
self.net = pbp.construct_PBP_network(n_hidden, X_train.shape[1])
# We iterate the learning process
pbp.train_PBP_network(self.net, X_train, y_train_normalized, n_epochs)
def __init__(self, X_train, y_train, n_hidden, n_epochs = 40,
normalize = False):
"""
Constructor for the class implementing a Bayesian neural network
trained with the probabilistic back propagation method.
@param X_train Matrix with the features for the training data.
@param y_train Vector with the target variables for the
training data.
@param n_hidden Vector with the number of neurons for each
hidden layer.
@param n_epochs Numer of epochs for which to train the
network. The recommended value 40 should be
enough.
@param normalize Whether to normalize the input features. This
is recommended unles the input vector is for
example formed by binary features (a
fingerprint). In that case we do not recommend
to normalize the features.
"""
# We normalize the training data to have zero mean and unit standard
# deviation in the training set if necessary
if normalize:
self.std_X_train = np.std(X_train, 0)
self.std_X_train[ self.std_X_train == 0 ] = 1
self.mean_X_train = np.mean(X_train, 0)
else:
self.std_X_train = np.ones(X_train.shape[ 1 ])
self.mean_X_train = np.zeros(X_train.shape[ 1 ])
X_train = (X_train - np.full(X_train.shape, self.mean_X_train)) / \
np.full(X_train.shape, self.std_X_train)
self.mean_y_train = np.mean(y_train)
self.std_y_train = np.std(y_train)
y_train_normalized = (y_train - self.mean_y_train) / self.std_y_train
# We construct the network
self.net = pbp.construct_PBP_network(n_hidden, X_train.shape[ 1 ])
# We iterate the learning process
pbp.train_PBP_network(self.net, X_train, y_train_normalized, n_epochs)
def re_train(self, X_train, y_train, n_epochs):
"""
Function that re-trains the network on some data.
@param X_train Matrix with the features for the training data.
@param y_train Vector with the target variables for the
training data.
@param n_epochs Numer of epochs for which to train the
network.
"""
# We normalize the training data
X_train = (X_train - np.full(X_train.shape, self.mean_X_train)) / \
np.full(X_train.shape, self.std_X_train)
y_train_normalized = (y_train - self.mean_y_train) / self.std_y_train
pbp.train_PBP_network(self.net, X_train, y_train_normalized, n_epochs)
def re_train(self, X_train, y_train, n_epochs):
"""
Function that re-trains the network on some data.
@param X_train Matrix with the features for the training data.
@param y_train Vector with the target variables for the
training data.
@param n_epochs Numer of epochs for which to train the
network.
"""
# We normalize the training data
X_train = (X_train - np.full(X_train.shape, self.mean_X_train)) / \
np.full(X_train.shape, self.std_X_train)
y_train_normalized = (y_train - self.mean_y_train) / self.std_y_train
pbp.train_PBP_network(self.net, X_train, y_train_normalized, n_epochs)
