Hidden Sequences

Vanilla RNN 모델

X = tf.keras.Input(shape=[20])
H = tf.keras.layers.Embedding(88585, 28)(X)
H = tf.keras.layers.SimpleRNN(32)(H)
Y = tf.keras.layers.Dense(1, activation="sigmoid")(H)

with Hidden Sequences

X = tf.keras.Input(shape=[20])
H = tf.keras.layers.Embedding(88585, 28)(X)
H = tf.keras.layers.SimpleRNN(32, return_sequences=True)(H)
H = tf.keras.layers.GlobalAveragePooling1D()(H)
Y = tf.keras.layers.Dense(1, activation="sigmoid")(H)