Deep Learning By Example

Cost function

Before defining our cost function, we need to define how long we are going to train and how we should define the learning rate:

#Number of training epochsnum_epochs = 700# Defining our learning rate iterations (decay)learning_rate = tf.train.exponential_decay(learning_rate=0.0008,                                          global_step=1,                                          decay_steps=train_input_values.shape[0],                                          decay_rate=0.95,                                          staircase=True)# Defining our cost function - Squared Mean Errormodel_cost = tf.nn.l2_loss(activation_output - output_values, name="squared_error_cost")# Defining our Gradient Descentmodel_train = tf.train.GradientDescentOptimizer(learning_rate).minimize(model_cost)

Now, it's time to execute our computational graph through the session variable.

So first off, we need to initialize ...