قارن الطرق

	أوتوفورمر: مُحوّل التفكيك للتنبؤ بالسلاسل الزمنية طويلة الأمد	نموذج الذاكرة ليجندر مع تحسين التردد (FiLM)
المجال	التعلم العميق	التعلم العميق
العائلة	Machine learning	Machine learning
سنة النشأة	2021	2022
صاحب الطريقة	Haixu Wu et al. (Tsinghua)	Tian Zhou et al.
النوع	Decomposition-based deep forecasting model	Frequency-domain time-series forecasting model
المصدر التأسيسي	Wu, H., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34.	Zhou, T., Ma, Z., Wen, Q., Sun, L., Yao, T., Yin, W., & Jin, R. (2022). FiLM: Frequency improved Legendre memory model for long-term time series forecasting. NeurIPS.
الأسماء البديلة	Auto-Correlation Transformer, Decomposition Transformer, Series Decomposition Forecaster, Oto-Korelasyon Ayrışım Transformer	Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli
ذات صلة	4	3
الملخص	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.	FiLM is a long-term time-series forecasting architecture introduced by Tian Zhou and colleagues at NeurIPS 2022. It combines Legendre polynomial projections of the historical input with learnable frequency-domain filters applied to the resulting coefficient sequences. By representing history as a compact set of polynomial coefficients and filtering those coefficients in the frequency domain, FiLM enables efficient extrapolation over long prediction horizons without the quadratic cost of full self-attention.