Linganisha mbinu

	TimesNet: Uundaji wa Miundo Mikuu ya 2D ya Muda kwa Mfululizo wa Wakati	Autoformer: Transformer ya Uharibifu kwa Utabiri wa Milipuko ya Muda Mrefu	PatchTST
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning	Machine learning
Mwaka wa asili	2023	2021	2023
Mwanzilishi	Haixu Wu et al.	Haixu Wu et al. (Tsinghua)	Nie, Y. et al.
Aina	2D convolutional time-series model	Decomposition-based deep forecasting model	Transformer for time series forecasting
Chanzo asilia	Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. ICLR.	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.
Majina mbadala	Temporal 2D-Variation Network, TimesNet Model, 2D Time-Series Network, Zamansal 2B Varyasyon Ağı	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
Zinazohusiana	2	4	3
Muhtasari	TimesNet is a general-purpose time-series model introduced by Wu et al. at ICLR 2023. Its central idea is that univariate or multivariate time series can be reinterpreted as collections of two-dimensional temporal maps by reshaping the 1D signal according to its dominant periodicities, detected via Fast Fourier Transform. This 1D-to-2D transformation exposes both intraperiod patterns (within one cycle) and interperiod trends (across cycles), enabling powerful 2D convolutional architectures to model temporal variation.	Autoformer is a deep learning architecture for long-term time-series forecasting, introduced by Wu et al. from Tsinghua University at NeurIPS 2021. It replaces the standard self-attention mechanism with an Auto-Correlation mechanism that exploits periodic dependencies in the frequency domain, and embeds a progressive series decomposition block throughout the encoder and decoder to separately model trend and seasonal components.	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.