HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Time Series Forecasting On Etth2 720 2

평가 지표

MAE

MSE

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	MAE	MSE	Paper Title	Repository
Transformer	0.434	0.2853	Long-term series forecasting with Query Selector -- efficient model of sparse attention
PatchMixer	0.374	0.217	PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
FiLM	0.396	0.241	FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
Informer	0.338	0.181	Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
PatchTST/64	0.38	0.223	A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
SegRNN	0.365	0.205	SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
NLinear	0.381	0.225	Are Transformers Effective for Time Series Forecasting?
SCINet	0.429	0.286	SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
AutoCon	0.344	0.177	Self-Supervised Contrastive Learning for Long-term Forecasting
QuerySelector	0.413	0.2585	Long-term series forecasting with Query Selector -- efficient model of sparse attention
DLinear	0.426	0.276	Are Transformers Effective for Time Series Forecasting?

0 of 11 row(s) selected.