Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective

arXiv:2402.11463v1 Announce Type: new
Abstract: In long-term time series forecasting (LTSF) tasks, existing deep learning models overlook the crucial characteristic that discrete time series originate from underlying continuous dynamic systems, resulting in a lack of extrapolation and evolution capabilities. Recognizing the chaotic nature of real-world data, our model, \textbf{\textit{Attraos}}, incorporates chaos theory into LTSF, perceiving real-world time series as observations from unknown high-dimensional chaotic dynamic systems. Under the concept of attractor invariance, Attraos utilizes the proposed multi-scale dynamic memory unit …

abstract arxiv capabilities chaos continuous cs.ai cs.lg data deep learning dynamic evolution forecasting long-term memory nature nlin.cd perspective series systems tasks time series time series forecasting type world