HyperAI초신경

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

한국어

HyperAI초신경

Sequential Image Classification On Sequential 1

평가 지표

Unpermuted Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Unpermuted Accuracy	Paper Title	Repository
S4	91.80%	Efficiently Modeling Long Sequences with Structured State Spaces	-
SMPConv	84.86%	SMPConv: Self-moving Point Representations for Continuous Convolution	-
Transformer (self-attention) (Trinh et al., 2018)	62.2%	Learning Longer-term Dependencies in RNNs with Auxiliary Losses	-
Sparse Combo Net	65.72	RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks	-
MultiresConv	93.15%	Sequence Modeling with Multiresolution Convolutional Memory	-
LSSL	84.65%	Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers	-
CKCNN (1M)	63.74%	CKConv: Continuous Kernel Convolution For Sequential Data	-
LRU	89.0	Resurrecting Recurrent Neural Networks for Long Sequences	-
LipschitzRNN	64.2	Lipschitz Recurrent Neural Networks	-
FlexTCN-6	80.82%	FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes	-
Trellis Network	73.42%	Trellis Networks for Sequence Modeling	-
UR-GRU	74.4%	Improving the Gating Mechanism of Recurrent Neural Networks	-
CKCNN (100k)	62.25%	CKConv: Continuous Kernel Convolution For Sequential Data	-

0 of 13 row(s) selected.

Sequential Image Classification On Sequential 1 | SOTA | HyperAI초신경