keraflow.layers.recurrent.SimpleRNN Class Reference

Fully-connected RNN where the output is to be fed back to input. More...

Inheritance diagram for keraflow.layers.recurrent.SimpleRNN:

Public Member Functions
def	__init__
Public Member Functions inherited from keraflow.layers.recurrent.Recurrent
def	__init__

Detailed Description

Fully-connected RNN where the output is to be fed back to input.

• input_shape: 3D, (nb_samples, sequence_length, input_dim)
• output_shape (return_sequences=True): 3D, (nb_samples, sequence_length, output_dim)
• output_shape (return_sequences=False): 2D, (nb_samples, output_dim)
• parameters:
  • W: (input_dim, output_dim)
  • U: (output_dim, output_dim)
  • b: (output_dim,)

Constructor & Destructor Documentation

def keraflow.layers.recurrent.SimpleRNN.__init__	(		self,
			output_dim,
			init = 'glorot_uniform',
			inner_init = 'orthogonal',
			activation = 'tanh',
			dropout_W = 0.,
			dropout_U = 0.,
			return_sequences = False,
			go_backwards = False,
			stateful = False,
			unroll = False,
			kwargs
	)

Parameters

output_dim	int. The output dimension of the layer.
init	str/function. Function to initialize W (input to hidden transformation). See Initializations.
inner_init	str/function. Function to initialize U (hidden to hidden transformation). See Initializations.
activation	str/function. Activation function applied on the output. See Activations.
dropout_W	float between 0 and 1. Fraction of the input units to drop for input gates.
dropout_U	float between 0 and 1. Fraction of the input units to drop for recurrent connections.
return_sequences	Boolean. See Recurrent.__init__
go_backwards	Boolean. See Recurrent.__init__
stateful	Boolean. See Recurrent.__init__
unroll	Boolean. See Recurrent.__init__
kwargs	see Layer.__init__.

• Dropout reference: A Theoretically Grounded Application of Dropout in Recurrent Neural Networks