Deep Learning Quick Reference

Neural network architecture

Now that we've defined the input and output, we can take a look at the code for the network.

from keras.layers import Input, Densefrom keras.models import Modeldef build_network(input_features=None):    inputs = Input(shape=(input_features,), name="input")    x = Dense(32, activation='relu', name="hidden")(inputs)    prediction = Dense(1, activation='linear', name="final")(x)    model = Model(inputs=inputs, outputs=prediction)    model.compile(optimizer='adam', loss='mean_absolute_error')    return model

That's all there is to it! We can then use this code to build a neural network instance suitable for our problem simply by calling it, as follows:

model = build_network(input_features=10)

Before we get to that, however, let's review ...