pyanno4rt.learning_model.frequentist.addons._neural_network_architectures

Neural network architectures.

Overview

Function

build_iocnn(input_shape, output_shape, labels, hyperparameters, squash_output)	Build the input-output convex neural network architecture with the functional API.
build_standard_nn(input_shape, output_shape, labels, hyperparameters, squash_output)	Build the standard neural network architecture with the functional API.

Functions

pyanno4rt.learning_model.frequentist.addons._neural_network_architectures.build_iocnn(input_shape, output_shape, labels, hyperparameters, squash_output)

Build the input-output convex neural network architecture with the functional API.

Parameters:

• input_shape (int) – Shape of the input features.

• output_shape (int) – Shape of the output labels.

• hyperparameters (dict) – Dictionary with the hyperparameter names and values for the neural network outcome prediction model.

• squash_output (bool) – Indicator for the use of a sigmoid activation function in the output layer.

Returns:

Instance of the class Functional, which provides a functional input-output convex neural network architecture.

Return type:

object of class ‘Functional’

pyanno4rt.learning_model.frequentist.addons._neural_network_architectures.build_standard_nn(input_shape, output_shape, labels, hyperparameters, squash_output)

Build the standard neural network architecture with the functional API.

Parameters:

• input_shape (int) – Shape of the input features.

• output_shape (int) – Shape of the output labels.

• hyperparameters (dict) – Dictionary with the hyperparameter names and values for the neural network outcome prediction model.

• squash_output (bool) – Indicator for the use of a sigmoid activation function in the output layer.

Returns:

Instance of the class Functional, which provides a functional standard neural network architecture.

Return type:

object of class ‘Functional’