Support stateful=True on the LMU (and other RNN flags)

[arvoelke]

The LMU layer currently accepts return_sequences and passes that through to tf.keras.layers.RNN with the created LMUCell. However, there are a number of other RNN flags that are ignored (https://www.tensorflow.org/api_docs/python/tf/keras/layers/RNN):

• return_state
• go_backwards
• stateful
• unroll
• time_major

In order to use any of these additional flags, the LMUCell must be invoked directly then and passed to tf.keras.layers.RNN alongside the flags. Supporting the flags at the layer level would mirror the pattern for other recurrent layers such as tf.keras.layers.LSTM.

[Ondrysak]

@arvoelke does the absence of support for go_backwards mean that using LMU in Bidirectional manner is not going to perform as expected using the standard keras Bidirectional wrapper, but only if using LMU layer notLMUCell?

Is something something like this going to work as expected?

x = layers.Bidirectional(tf.keras.layers.RNN(
    keras_lmu.LMUCell(
        memory_d=1,
        order=64 ,
        theta=maxlen,     
    hidden_cell=tf.keras.layers.SimpleRNNCell(units=64),
        hidden_to_memory=False,
        memory_to_memory=False,
        input_to_hidden=True,
        kernel_initializer="ones",
    )))(x)

[arvoelke]

That example should work as expected. If you were to try tf.keras.layers.Bidirectional(keras_lmu.LMU(...)) instead then you should see a KeyError: 'go_backwards' (at least I do on tensorflow==2.3.1).