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

العربية

Time Series Forecasting On Etth2 336 2

المقاييس

MAE

MSE

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	MAE	MSE	Paper Title	Repository
SegRNN	0.345	0.18	SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
DLinear	0.367	0.209	Are Transformers Effective for Time Series Forecasting?
FiLM	0.367	0.204	FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
Informer	0.323	0.166	Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
PatchMixer	0.332	0.166	PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
PatchTST/64	0.336	0.171	A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
NLinear	0.355	0.194	Are Transformers Effective for Time Series Forecasting?
Transformer	0.3805	0.2191	Long-term series forecasting with Query Selector -- efficient model of sparse attention
SCINet	0.329	0.166	SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
QuerySelector	0.371	0.2088	Long-term series forecasting with Query Selector -- efficient model of sparse attention

0 of 10 row(s) selected.