neural_network.back_propagation_neural_network

A Framework of Back Propagation Neural Network (BP) model

Easy to use:

• add many layers as you want ! ! !

• clearly see how the loss decreasing

Easy to expand:

• more activation functions

• more loss functions

• more optimization method

Author: Stephen Lee Github : https://github.com/RiptideBo Date: 2017.11.23

Classes

BPNN	Back Propagation Neural Network model
DenseLayer	Layers of BP neural network

Functions

example()
sigmoid(→ numpy.ndarray)

Module Contents

class neural_network.back_propagation_neural_network.BPNN

Back Propagation Neural Network model

add_layer(layer)

build()

cal_loss(ydata, ydata_)

plot_loss()

summary()

train(xdata, ydata, train_round, accuracy)

ax_loss

fig_loss

layers = []

train_mse = []

class neural_network.back_propagation_neural_network.DenseLayer(units, activation=None, learning_rate=None, is_input_layer=False)

Layers of BP neural network

back_propagation(gradient)

cal_gradient()

forward_propagation(xdata)

initializer(back_units)

activation = None

bias = None

is_input_layer = False

learn_rate = None

units

weight = None

neural_network.back_propagation_neural_network.example()

neural_network.back_propagation_neural_network.sigmoid(x: numpy.ndarray) → numpy.ndarray