Comparer des méthodes

	FiLM: Modèle de mémoire de Legendre à fréquence améliorée	TSMixer : une architecture tout MLP pour la prévision de séries temporelles
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2022	2023
Auteur d'origine	Tian Zhou et al.	Si-An Chen et al. (Google)
Type	Frequency-domain time-series forecasting model	All-MLP multivariate time-series forecasting model
Source fondatrice	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 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
Apparentées	3	3
Résumé	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.