Deep Learning with Keras

Sequential composition

The first one is the sequential composition, where different predefined models are stacked together in a linear pipeline of layers similar to a stack or a queue. In Chapter 1, Neural Networks Foundations, we saw a few examples of sequential pipelines. For instance:

model = Sequential()model.add(Dense(N_HIDDEN, input_shape=(784,)))model.add(Activation('relu'))model.add(Dropout(DROPOUT))model.add(Dense(N_HIDDEN))model.add(Activation('relu'))model.add(Dropout(DROPOUT))model.add(Dense(nb_classes))model.add(Activation('softmax'))model.summary()