Sammenlign metoder

	FEDformer: Frekvensforsterket dekomponert transformator	FiLM: Frequency Improved Legendre Memory Model	TSMixer: All-MLP-arkitektur for tidsserieprognoser
Fagfelt	Dyp læring	Dyp læring	Dyp læring
Familie	Machine learning	Machine learning	Machine learning
Opprinnelsesår	2022	2022	2023
Opphavsperson	Tian Zhou et al.	Tian Zhou et al.	Si-An Chen et al. (Google)
Type	Frequency-domain decomposed Transformer for time-series forecasting	Frequency-domain time-series forecasting model	All-MLP multivariate time-series forecasting model
Opprinnelig kilde	Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R. (2022). FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. ICML.	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.	Chen, S.-A., Li, C.-L., Yoder, N., Arik, S. O., & Pfister, T. (2023). TSMixer: An all-MLP architecture for time series forecasting. Transactions on Machine Learning Research.
Alias	Frequency Enhanced Decomposed Transformer, FED-Transformer, Frequency Domain Transformer, Frekans Tabanlı Ayrıştırılmış Dönüştürücü	Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli	All-MLP Time Series Mixer, Time Series Mixer, TSMixer Forecasting Model, Zaman Serisi Karıştırıcı
Relaterte	3	3	3
Sammendrag	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.	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.	TSMixer is a multivariate time-series forecasting model introduced by Si-An Chen and colleagues at Google in 2023. It challenges the prevailing dominance of Transformer-based architectures by demonstrating that a simple stack of interleaved MLP layers — alternating between mixing along the time axis and mixing across feature channels — achieves strong forecasting accuracy while remaining computationally efficient and easy to interpret architecturally.