Vertaile menetelmiä

	Kaksisuuntainen RNN	Dilatoitu CNN	Porttiyksikkö (GRU)
Tieteenala	Syväoppiminen	Syväoppiminen	Syväoppiminen
Menetelmäperhe	Machine learning	Machine learning	Machine learning
Syntyvuosi	1997	2016	2014
Kehittäjä	Schuster, M. & Paliwal, K.K.	van den Oord, A. et al.; Bai, S., Kolter, J.Z. & Koltun, V.	Cho, K. et al.
Tyyppi	Recurrent neural network (sequence model)	Deep learning (dilated 1D convolutional network)	Gated recurrent neural network unit
Alkuperäislähde	Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681.	van den Oord, A. et al. (2016). WaveNet: A Generative Model for Raw Audio. arXiv.	Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP.
Rinnakkaisnimet	Çift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU	Dilate Edilmiş CNN (WaveNet / TCN), WaveNet, Temporal Convolutional Network, TCN	Kapılı Tekrarlayan Birim (GRU), gated recurrent unit, gated recurrent network
Liittyvät	5	5	5
Tiivistelmä	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.	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.	The Gated Recurrent Unit (GRU) is a gated recurrent neural network cell introduced by Cho and colleagues in 2014 that captures long-range dependencies in sequential data using update and reset gates, achieving performance comparable to LSTM with fewer parameters.