Building, compiling and visualising a three-layer neural network

three-layer-nn.py

from keras import models, layers, optimizers, regularizers
from keras.utils.vis_utils import model_to_dot
from IPython.display import SVG

# Building the model
nn2 = models.Sequential()
nn2.add(layers.Dense(128, input_shape=(X_train.shape[1],), activation='relu'))
nn2.add(layers.Dense(256, activation='relu'))
nn2.add(layers.Dense(256, activation='relu'))
nn2.add(layers.Dense(1, activation='linear'))

# Compiling the model
nn2.compile(loss='mean_squared_error',
            optimizer='adam',
            metrics=['mean_squared_error'])

# Printing the model summary
print(nn2.summary())

# Visualising the neural network
SVG(model_to_dot(nn2, show_layer_names=False, show_shapes=True).create(prog='dot', format='svg'))

# Training the model
nn2_history = nn2.fit(X_train,
                  y_train,
                  epochs=100,
                  batch_size=256,
                  validation_split = 0.1)