الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Time Series Forecasting On Etth1 720 2

المقاييس

MAE

MSE

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	MAE	MSE	Paper Title	Repository
DLinear	0.359	0.189	Are Transformers Effective for Time Series Forecasting?
Transformer	0.4213	0.2501	Long-term series forecasting with Query Selector -- efficient model of sparse attention
QuerySelector	0.373	0.2136	Long-term series forecasting with Query Selector -- efficient model of sparse attention
Informer	0.357	0.201	Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
SCINet	0.25	0.099	SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
PatchTST/64	0.236	0.087	A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
FiLM	0.24	0.09	FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
AutoCon	0.223	0.078	Self-Supervised Contrastive Learning for Long-term Forecasting
SegRNN	0.233	0.085	SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
PatchMixer	0.243	0.093	PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
NLinear	0.226	0.08	Are Transformers Effective for Time Series Forecasting?
Parallel Series Transformer	0.286	0.129	How Features Benefit: Parallel Series Embedding for Multivariate Time Series Forecasting with Transformer

0 of 12 row(s) selected.