neupy.algorithms.Adadelta

class neupy.algorithms.Adadelta[source]

Adadelta algorithm.

Parameters:
rho : float

Decay rate. Value need to be between 0 and 1. Defaults to 0.95.

epsilon : float

Value need to be greater than 0. Defaults to 1e-7.

step : float

Learning rate, defaults to 1.0. Original paper doesn’t have learning rate specified in the paper. Step value equal to 1.0 allow to achive the same effect, since multiplication by one won’t have any effect on the update.

batch_size : int or None

Set up min-batch size. The None value will ensure that all data samples will be propagated through the network at once. Defaults to 128.

regularizer : function or None

Network’s regularizer.

network : list, tuple or LayerConnection instance

Network’s architecture. There are a few ways to define it.

  • List of layers. For instance, [Input(2), Tanh(4), Relu(1)].
  • Constructed layers. For instance, Input(2) >> Tanh(4) >> Relu(1).
loss : str or function

Error/loss function. Defaults to mse.

  • mae - Mean Absolute Error.
  • mse - Mean Squared Error.
  • rmse - Root Mean Squared Error.
  • msle - Mean Squared Logarithmic Error.
  • rmsle - Root Mean Squared Logarithmic Error.
  • categorical_crossentropy - Categorical cross entropy.
  • binary_crossentropy - Binary cross entropy.
  • binary_hinge - Binary hinge entropy.
  • categorical_hinge - Categorical hinge entropy.
  • Custom function which accepts two mandatory arguments. The first one is expected value and the second one is predicted value. Example:
def custom_func(expected, predicted):
    return expected - predicted
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.

References

[1] Matthew D. Zeiler,
ADADELTA: An Adaptive Learning Rate Method https://arxiv.org/pdf/1212.5701.pdf

Examples

>>> import numpy as np
>>> from neupy import algorithms
>>> from neupy.layers import *
>>>
>>> x_train = np.array([[1, 2], [3, 4]])
>>> y_train = np.array([[1], [0]])
>>>
>>> network = Input(2) >> Sigmoid(3) >> Sigmoid(1)
>>> optimizer = algorithms.Adadelta(network)
>>> optimizer.train(x_train, y_train)
Attributes:
errors : list

Information about errors. It has two main attributes, namely train and valid. These attributes provide access to the training and validation errors respectively.

last_epoch : int

Value equals to the last trained epoch. After initialization it is equal to 0.

n_updates_made : int

Number of training updates applied to the network.

Methods

predict(X) Predicts output for the specified input.
train(X_train, y_train, X_test=None, y_test=None, epochs=100) Train network. You can control network’s training procedure with epochs parameter. The X_test and y_test should be presented both in case network’s validation required after each training epoch.
fit(*args, **kwargs) Alias to the train method.
epsilon = None[source]
init_train_updates()[source]
options = {'batch_size': Option(class_name='GradientDescent', value=IntProperty(name="batch_size")), 'epsilon': Option(class_name='Adadelta', value=NumberProperty(name="epsilon")), 'loss': Option(class_name='BaseOptimizer', value=FunctionWithOptionsProperty(name="loss")), 'regularizer': Option(class_name='BaseOptimizer', value=Property(name="regularizer")), 'rho': Option(class_name='Adadelta', value=ProperFractionProperty(name="rho")), '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='Adadelta', value=ScalarVariableProperty(name="step")), 'target': Option(class_name='BaseOptimizer', value=Property(name="target")), 'verbose': Option(class_name='Verbose', value=VerboseProperty(name="verbose"))}[source]
rho = None[source]
step = None[source]