Comparar métodos
Examine os métodos selecionados lado a lado; as linhas que diferem ficam destacadas.
| Unidade Recorrente Gated (GRU)× | LSTM× | PatchTST× | |
|---|---|---|---|
| Área | Aprendizado profundo | Aprendizado profundo | Aprendizado profundo |
| Família | Machine learning | Machine learning | Machine learning |
| Ano de origem≠ | 2014 | 1997 | 2023 |
| Autor original≠ | Cho, K. et al. | Hochreiter, S. & Schmidhuber, J. | Nie, Y. et al. |
| Tipo≠ | Gated recurrent neural network unit | Recurrent neural network (gated memory cell) | Transformer for time series forecasting |
| Fonte seminal≠ | Cho, K. et al. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. EMNLP. link ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗ |
| Outros nomes≠ | Kapılı Tekrarlayan Birim (GRU), gated recurrent unit, gated recurrent network | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer |
| Relacionados≠ | 5 | 5 | 3 |
| Resumo≠ | 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. | 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. | PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting. |
| ScholarGateConjunto de dados ↗ |
|
|
|