手法を比較

	Dilated CNN	Bidirectional RNN	シーケンス・ツー・シーケンスモデル
分野	深層学習	深層学習	深層学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2016	1997	2014
提唱者	van den Oord, A. et al.; Bai, S., Kolter, J.Z. & Koltun, V.	Schuster, M. & Paliwal, K.K.	Sutskever, I.; Cho, K.
種類	Deep learning (dilated 1D convolutional network)	Recurrent neural network (sequence model)	Encoder-decoder neural network (deep learning)
原典	van den Oord, A. et al. (2016). WaveNet: A Generative Model for Raw Audio. arXiv.	Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681.	Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS.
別名	Dilate Edilmiş CNN (WaveNet / TCN), WaveNet, Temporal Convolutional Network, TCN	Çift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU	Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning
関連	5	5	5
概要	A Dilated CNN is a one-dimensional convolutional network whose receptive field grows exponentially with depth, letting it model long-range structure in time series and audio signals. WaveNet (van den Oord et al., 2016) and the Temporal Convolutional Network of Bai, Kolter and Koltun (2018) are the prominent members of this family.	A Bidirectional RNN, introduced by Schuster and Paliwal in 1997, processes a sequence in both forward and backward directions so that every position has access to its full surrounding context. With LSTM or GRU cells (BiLSTM/BiGRU) it is the standard approach for named-entity recognition, sequence labelling, and speech recognition.	The sequence-to-sequence (Seq2Seq) model, introduced by Sutskever, Vinyals and Le and by Cho and colleagues in 2014, is an encoder-decoder neural network that maps a variable-length input sequence to a variable-length output sequence. It is the foundation of machine translation, text summarization, dialogue systems and code generation.