Chapter overviewIntroductory
In which chapter of the book is FEDformer introduced, and what is its primary purpose?
FEDformer is introduced in Chapter 2 of the book. Its primary purpose is long-term time series forecasting, achieved through a frequency-enhanced decomposed Transformer that combines seasonal-trend decomposition with Fourier representations.
Chapter 2, titled "Fedformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting," presents FEDformer. The model is designed for long-term forecasting and operates by selecting subsets of frequency components and working in the spectral domain, which helps capture key patterns in time series data.
Key points
- FEDformer appears in Chapter 2.
- The chapter title explicitly states its purpose: long-term series forecasting.
- The model integrates seasonal-trend decomposition with Fourier representations.
- It operates in the spectral domain by selecting frequency components.
Source:AI for Time Series_ Volume 1_ Unlocking Patterns with Deep Learning· Fedformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting· p. 6–14
Related questions
AI for Time Series_ Volume 1_ Unlocking Patterns with Deep Learning
Min Wu;Emadeldeen Eldele;Zhenghua Chen;Shirui Pan;Qingsong Wen;Xiaoli Li;
First edition · CRC Press