Vertaile menetelmiä

	FiLM: Frequency Improved Legendre Memory Model	FEDformer: Taajuusparannettu hajotettu Transformer	Tilamallinnus (Kalman-suodin)
Tieteenala	Syväoppiminen	Syväoppiminen	Ekonometria
Menetelmäperhe	Machine learning	Machine learning	Regression model
Syntyvuosi	2022	2022	1990
Kehittäjä	Tian Zhou et al.	Tian Zhou et al.	Harvey; Durbin & Koopman (state space treatment); Kalman filter
Tyyppi	Frequency-domain time-series forecasting model	Frequency-domain decomposed Transformer for time-series forecasting	State space time series model
Alkuperäislähde	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.	Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML.	Harvey, A. C. (1990). Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge University Press.
Rinnakkaisnimet	Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli	Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü	state space, Kalman filter, unobserved components model, Durum Uzayı Modeli (State Space / Kalman Filter)
Liittyvät	3	3	4
Tiivistelmä	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.	FEDformer is a Transformer-based architecture for long-term multivariate time-series forecasting, introduced by Zhou et al. at ICML 2022. Its core innovation is the combination of seasonal-trend decomposition with frequency-domain attention: instead of computing full token-to-token attention in the time domain, FEDformer projects queries, keys, and values into the frequency domain via Fourier or wavelet transforms and operates on a randomly selected subset of frequency components, achieving linear complexity while preserving global temporal structure.	A state space model is a general time series framework that describes a series through unobserved (latent) state variables linked by a measurement equation and a transition equation, with the states estimated in real time by the Kalman filter. Developed in the state space tradition of Harvey (1990) and Durbin & Koopman (2012), it nests ARIMA and exponential smoothing as special cases.