QBoard » Artificial Intelligence & ML » AI and ML - Conceptual » The difference between RNN Decoder and RNN

The difference between RNN Decoder and RNN

  • We are only using the RNN decoder (without encoder) for text generation, how is RNN decoder different from pure RNN operation?

    RNN Decoder in TensorFlow: https://www.tensorflow.org/api_docs/python/tf/contrib/seq2seq/dynamic_rnn_decoder

    Pure
    RNN in TensorFlow: https://www.tensorflow.org/api_docs/python/tf/nn/dynamic_rnn

    Thanks
    for your time
      June 11, 2019 3:57 PM IST
    0
  • The Encoder-Decoder architecture with recurrent neural networks has become an effective and standard approach for both neural machine translation (NMT) and sequence-to-sequence (seq2seq) prediction in general.

    The key benefits of the approach are the ability to train a single end-to-end model directly on source and target sentences and the ability to handle variable length input and output sequences of text.

      June 14, 2019 11:26 AM IST
    0
  • RNN Decoder is sequence to sequence mapping model. In combination with Encoder takes a sequence as input and generates another sequence as output. In many to many sequence learning setups, the input is a sequence of vectors and the output is another sequence of vectors.

    Eg: Speech Wave to Text, Language Translation etc

    In General We use Normal RNN for one to one sequence learning setup.

    Eg: Next Character Prediction.

      June 11, 2019 4:02 PM IST
    0