neupy.algorithms.memory.cmac module

class neupy.algorithms.memory.cmac.CMAC[source]

Cerebellar Model Articulation Controller (CMAC) Network based on memory.

Parameters:
quantization : int

Network transforms every input to discrete value. Quantization value contol number of total possible categories after quantization, defaults to 10.

associative_unit_size : int

Number of associative blocks in memory, defaults to 2.

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.

Notes

  • Network always use Mean Absolute Error (MAE).
  • Network works for multi dimensional target values.

Examples

>>> import numpy as np
>>> from neupy.algorithms import CMAC
>>>
>>> train_space = np.linspace(0, 2 * np.pi, 100)
>>> test_space = np.linspace(np.pi, 2 * np.pi, 50)
>>>
>>> X_train = np.reshape(train_space, (100, 1))
>>> X_test = np.reshape(test_space, (50, 1))
>>>
>>> y_train = np.sin(X_train)
>>> y_test = np.sin(X_test)
>>>
>>> cmac = CMAC(
...     quantization=100,
...     associative_unit_size=32,
...     step=0.2,
... )
...
>>> cmac.train(X_train, y_train, epochs=100)
>>>
>>> predicted_test = cmac.predict(X_test)
>>> cmac.score(y_test, predicted_test)
0.0023639417543036569
Attributes:
weight : dict

Network’s weight that contains memorized patterns.

Methods

predict(X) Predicts output for the specified input.
train(X_train, y_train, X_test=None, y_test=None, epochs=100) Trains the network to the data X. Network trains until maximum number of epochs was reached.
fit(*args, **kwargs) Alias to the train method.
associative_unit_size = None[source]
get_memory_coords(quantized_value)[source]
get_result_by_coords(coords)[source]
one_training_update(X_train, y_train)[source]

Function would be trigger before run all training procedure related to the current epoch.

Parameters:
epoch : int

Current epoch number.

options = {'associative_unit_size': Option(class_name='CMAC', value=IntProperty(name="associative_unit_size")), 'quantization': Option(class_name='CMAC', value=IntProperty(name="quantization")), '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"))}[source]
predict(X)[source]
quantization = None[source]
quantize(X)[source]
score(X, y)[source]
train(X_train, y_train, X_test=None, y_test=None, epochs=100)[source]

Method train neural network.

Parameters:
X_train : array-like
y_train : array-like or None
X_test : array-like or None
y_test : array-like or None
epochs : int

Defaults to 100.

epsilon : float or None

Defaults to None.