方法对比

	长短期记忆网络	自编码器	Transformer (NLP)
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	1997	2006	2017
提出者	Hochreiter, S. & Schmidhuber, J.	Hinton, G.E. & Salakhutdinov, R.R.	Vaswani, A. et al.
类型	Recurrent neural network (gated memory cell)	Neural network (encoder-decoder)	Attention-based deep neural network
开创性文献	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.
别名	LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Transformer Modeli (NLP), attention-based language model, self-attention network, transformer NLP
相关	5	4	4
摘要	LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.	An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.	The Transformer is an attention-based deep learning model, introduced by Vaswani and colleagues in 2017, that performs text classification, named-entity recognition, and language modelling by letting every token in a sequence attend directly to every other token. It replaced earlier recurrent designs with a self-attention mechanism that processes whole sequences in parallel.