قارن الطرق

	Koopa: متنبئات كوبمان للمتسلسلات الزمنية غير المستقرة	المحول غير المستقر (Non-stationary Transformer)
المجال	التعلم العميق	التعلم العميق
العائلة	Machine learning	Machine learning
سنة النشأة	2023	2022
صاحب الطريقة	Yong Liu et al.	Yong Liu et al.
النوع	Koopman operator-based time-series forecasting model	Transformer-based time-series forecasting model
المصدر التأسيسي	Liu, Y., Li, C., Wang, J., & Long, M. (2023). Koopa: Learning non-stationary time series dynamics with Koopman predictors. NeurIPS.	Liu, Y., Wu, H., Wang, J., & Long, M. (2022). Non-stationary transformers: Exploring the stationarity in time series forecasting. NeurIPS.
الأسماء البديلة	Koopman Predictor, Koopman-based Time-Series Model, Koopa Forecaster, Koopman Tahmincisi	NS-Transformer, Non-stationary Transformer Network, Stationarization-based Transformer, Durağan-Olmayan Transformer
ذات صلة	3	3
الملخص	Koopa is a deep learning model for time-series forecasting introduced by Yong Liu, Chang Li, Jianmin Wang, and Mingsheng Long at NeurIPS 2023. It addresses the challenge of non-stationarity by disentangling time series into stationary and non-stationary components, then modeling the non-stationary dynamics using a learned approximation of the Koopman operator — a mathematical framework that lifts nonlinear systems into a linear space for tractable long-horizon prediction.	Non-stationary Transformer is a Transformer-based time-series forecasting architecture introduced by Yong Liu, Haixu Wu, Jianmin Wang, and Mingsheng Long at NeurIPS 2022. It addresses a fundamental tension in applying Transformers to real-world time series: over-stationarization during preprocessing strips out non-stationary signals that carry predictive information, while raw non-stationary inputs cause attention to collapse. The model resolves this through series stationarization paired with a novel de-stationary attention mechanism that restores the original temporal distribution in predictions.