Порівняння методів

	FiLM: Покращена модель пам'яті Лежандра на основі частоти	Informer
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2022	2021
Автор методу	Tian Zhou et al.	Zhou, H. et al.
Тип	Frequency-domain time-series forecasting model	Transformer (ProbSparse self-attention)
Основоположне джерело	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, H. et al. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. AAAI.
Інші назви	Frequency Improved Legendre Memory, FiLM Forecaster, Legendre Frequency Model, Frekans Tabanlı Legendre Bellek Modeli	Informer — Uzun Dizi Transformer Tahmini, Informer transformer, ProbSparse attention forecaster
Пов'язані	3	5
Підсумок	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.	Informer is a Transformer-based model introduced by Zhou et al. in 2021 for long-sequence time-series forecasting, using a ProbSparse self-attention mechanism that lowers the computational complexity of the standard Transformer to O(L log L). It is built for problems that demand predictions across thousands of future steps.