neural_network.back_propagation_neural_network
==============================================

.. py:module:: neural_network.back_propagation_neural_network

.. autoapi-nested-parse::

   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
-------

.. autoapisummary::

   neural_network.back_propagation_neural_network.BPNN
   neural_network.back_propagation_neural_network.DenseLayer


Functions
---------

.. autoapisummary::

   neural_network.back_propagation_neural_network.example
   neural_network.back_propagation_neural_network.sigmoid


Module Contents
---------------

.. py:class:: BPNN

   Back Propagation Neural Network model


   .. py:method:: add_layer(layer)


   .. py:method:: build()


   .. py:method:: cal_loss(ydata, ydata_)


   .. py:method:: plot_loss()


   .. py:method:: summary()


   .. py:method:: train(xdata, ydata, train_round, accuracy)


   .. py:attribute:: ax_loss


   .. py:attribute:: fig_loss


   .. py:attribute:: layers
      :value: []



   .. py:attribute:: train_mse
      :value: []



.. py:class:: DenseLayer(units, activation=None, learning_rate=None, is_input_layer=False)

   Layers of BP neural network


   .. py:method:: back_propagation(gradient)


   .. py:method:: cal_gradient()


   .. py:method:: forward_propagation(xdata)


   .. py:method:: initializer(back_units)


   .. py:attribute:: activation
      :value: None



   .. py:attribute:: bias
      :value: None



   .. py:attribute:: is_input_layer
      :value: False



   .. py:attribute:: learn_rate
      :value: None



   .. py:attribute:: units


   .. py:attribute:: weight
      :value: None



.. py:function:: example()

.. py:function:: sigmoid(x: numpy.ndarray) -> numpy.ndarray