ScholarGate
دستیار

مقایسهٔ روش‌ها

روش‌های انتخابی خود را کنار هم مرور کنید؛ ردیف‌های متفاوت برجسته شده‌اند.

LSTM×پچ‌تی‌اس‌تی×
حوزهیادگیری عمیقیادگیری عمیق
خانوادهMachine learningMachine learning
سال پیدایش19972023
پدیدآورHochreiter, S. & Schmidhuber, J.Nie, Y. et al.
نوعRecurrent neural network (gated memory cell)Transformer for time series forecasting
منبع بنیادینHochreiter, 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 ↗
نام‌های دیگرLSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cellsPatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
مرتبط53
خلاصهLSTM (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.
ScholarGateمجموعه‌داده
  1. v1
  2. 1 منابع
  3. PUBLISHED
  1. v1
  2. 2 منابع
  3. PUBLISHED

رفتن به جست‌وجو دریافت اسلایدها

ScholarGateمقایسهٔ روش‌ها: LSTM · PatchTST. بازیابی‌شده در 2026-06-17 از https://scholargate.app/fa/compare