neupy.algorithms.rbm module

class neupy.algorithms.rbm.RBM[source]

Boolean/Bernoulli Restricted Boltzmann Machine (RBM). Algorithm assumes that inputs are either binary values or values between 0 and 1.

Parameters:
n_visible : int

Number of visible units. Number of features (columns) in the input data.

n_hidden : int

Number of hidden units. The large the number the more information network can capture from the data, but it also mean that network is more likely to overfit.

batch_size : int

Size of the mini-batch. Defaults to 10.

weight : array-like, Tensorfow variable, Initializer or scalar

Default initialization methods you can find here. Defaults to Normal.

hidden_bias : array-like, Tensorfow variable, Initializer or scalar

Default initialization methods you can find here. Defaults to Constant(value=0).

visible_bias : array-like, Tensorfow variable, Initializer or scalar

Default initialization methods you can find here. Defaults to Constant(value=0).

step : float

Learning rate, defaults to 0.1.

show_epoch : int

This property controls how often the network will display information about training. It has to be defined as positive integer. For instance, number 100 mean that network shows summary at 1st, 100th, 200th, 300th … and last epochs.

Defaults to 1.

shuffle_data : bool

If it’s True than training data will be shuffled before the training. Defaults to True.

signals : dict, list or function

Function that will be triggered after certain events during the training.

verbose : bool

Property controls verbose output in terminal. The True value enables informative output in the terminal and False - disable it. Defaults to False.

References

[1] G. Hinton, A Practical Guide to Training Restricted
Boltzmann Machines, 2010. http://www.cs.toronto.edu/~hinton/absps/guideTR.pdf

Examples

>>> import numpy as np
>>> from neupy import algorithms
>>>
>>> data = np.array([
...     [1, 0, 1, 0],
...     [1, 0, 1, 0],
...     [1, 0, 0, 0],  # incomplete sample
...     [1, 0, 1, 0],
...
...     [0, 1, 0, 1],
...     [0, 0, 0, 1],  # incomplete sample
...     [0, 1, 0, 1],
...     [0, 1, 0, 1],
...     [0, 1, 0, 1],
...     [0, 1, 0, 1],
... ])
>>>
>>> rbm = algorithms.RBM(n_visible=4, n_hidden=1)
>>> rbm.train(data, epochs=100)
>>>
>>> hidden_states = rbm.visible_to_hidden(data)
>>> hidden_states.round(2)
array([[ 0.99],
       [ 0.99],
       [ 0.95],
       [ 0.99],
       [ 0.  ],
       [ 0.01],
       [ 0.  ],
       [ 0.  ],
       [ 0.  ],
       [ 0.  ]])

Methods

train(X_train, epochs=100) Trains network.
predict(X) Alias to the visible_to_hidden method.
visible_to_hidden(visible_input) Propagates data through the network and returns output from the hidden layer.
hidden_to_visible(hidden_input) Propagates output from the hidden layer backward to the visible.
gibbs_sampling(visible_input, n_iter=1) Makes Gibbs sampling n times using visible input.
fit(*args, **kwargs) Alias to the train method.
batch_size = None[source]
gibbs_sampling(visible_input, n_iter=1)[source]

Makes Gibbs sampling n times using visible input.

Parameters:
visible_input : 1d or 2d array
n_iter : int

Number of Gibbs sampling iterations. Defaults to 1.

Returns:
array-like

Output from the visible units after perfoming n Gibbs samples. Array will contain only binary units (0 and 1).

hidden_bias = None[source]
hidden_to_visible(hidden_input)[source]

Propagates output from the hidden layer backward to the visible.

Parameters:
hidden_input : array-like (n_samples, n_hidden_features)
Returns:
array-like
init_functions()[source]
init_methods()[source]
n_hidden = None[source]
n_visible = None[source]
one_training_update(X_train, y_train=None)[source]

Train one epoch.

Parameters:
X_train : array-like (n_samples, n_features)
Returns:
float
options = {'batch_size': Option(class_name='RBM', value=IntProperty(name="batch_size")), 'hidden_bias': Option(class_name='RBM', value=ParameterProperty(name="hidden_bias")), 'n_hidden': Option(class_name='RBM', value=IntProperty(name="n_hidden")), 'n_visible': Option(class_name='RBM', value=IntProperty(name="n_visible")), 'show_epoch': Option(class_name='BaseNetwork', value=IntProperty(name="show_epoch")), 'shuffle_data': Option(class_name='BaseNetwork', value=Property(name="shuffle_data")), 'signals': Option(class_name='BaseNetwork', value=Property(name="signals")), 'step': Option(class_name='BaseNetwork', value=NumberProperty(name="step")), 'verbose': Option(class_name='Verbose', value=VerboseProperty(name="verbose")), 'visible_bias': Option(class_name='RBM', value=ParameterProperty(name="visible_bias")), 'weight': Option(class_name='RBM', value=ParameterProperty(name="weight"))}[source]
predict(X)[source]
score(X, y=None)[source]

Compute the pseudo-likelihood of input samples.

Parameters:
X : array-like

Values of the visible layer

Returns:
float

Value of the pseudo-likelihood.

train(X_train, X_test=None, epochs=100)[source]

Train RBM.

Parameters:
X_train : 1D or 2D array-like
X_test : 1D or 2D array-like or None

Defaults to None.

epochs : int

Number of training epochs. Defaults to 100.

visible_bias = None[source]
visible_to_hidden(visible_input)[source]

Propagates data through the network and returns output from the hidden layer.

Parameters:
visible_input : array-like (n_samples, n_visible_features)
Returns:
array-like
weight = None[source]