Compară metode

	Autoformer	TimesNet: Modelare a Variației Temporale 2D pentru Serii de Timp
Domeniu	Învățare profundă	Învățare profundă
Familie	Machine learning	Machine learning
Anul apariției	2021	2023
Autorul original	Haixu Wu et al. (Tsinghua)	Haixu Wu et al.
Tip	Decomposition-based deep forecasting model	2D convolutional time-series model
Sursa seminală	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. ICLR.
Denumiri alternative	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Temporal 2D-Variation Network, TimesNet Model, 2D Time-Series Network, Zamansal 2B Varyasyon Ağı
Înrudite	4	2
Rezumat	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.	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.