Papers with Code · CC BY-SA 4.0

Sequential MNIST

아카이브 평가 30건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
SMPConv	Unpermuted Accuracy 99.75 Permuted Accuracy 99.10	SMPConv: Self-moving Point Representations for Continuous Convolution 2023-04-05	코드 1
LSSL	Unpermuted Accuracy 99.53% Permuted Accuracy 98.76%	Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers 2021-10-26	코드 1 · 코드 2
FlexTCN-4	Permuted Accuracy 98.72%	FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes 2021-10-15	코드 1
S4	Unpermuted Accuracy 99.63% Permuted Accuracy 98.70%	Efficiently Modeling Long Sequences with Structured State Spaces 2021-10-31	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
CKCNN (1M)	Unpermuted Accuracy 99.32% Permuted Accuracy 98.54%	CKConv: Continuous Kernel Convolution For Sequential Data 2021-02-04	코드 1
Modified LMU (165k)	Permuted Accuracy 98.49%	Parallelizing Legendre Memory Unit Training 2021-02-22	코드 1 · 코드 2
UnICORNN	Permuted Accuracy 98.4	UnICORNN: A recurrent model for learning very long time dependencies 2021-03-09	코드 1
HiPPO-LegS	Permuted Accuracy 98.3%	HiPPO: Recurrent Memory with Optimal Polynomial Projections 2020-08-17	코드 1 · 코드 2
CKCNN (100k)	Unpermuted Accuracy 99.31% Permuted Accuracy 98%	CKConv: Continuous Kernel Convolution For Sequential Data 2021-02-04	코드 1
ODE-LSTM	Permuted Accuracy 97.83%	Learning Long-Term Dependencies in Irregularly-Sampled Time Series 2020-06-08	코드 1 · 코드 2
coRNN	Unpermuted Accuracy 99.4% Permuted Accuracy 97.34%	Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies 2020-10-02	코드 1
Dense IndRNN	Unpermuted Accuracy 99.48% Permuted Accuracy 97.2%	Deep Independently Recurrent Neural Network (IndRNN) 2019-10-11	코드 1
Temporal Convolutional Network	Unpermuted Accuracy 99.0% Permuted Accuracy 97.2%	An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling 2018-03-04	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23 · 코드 24 · 코드 25 · 코드 26 · 코드 27 · 코드 28 · 코드 29 · 코드 30 · 코드 31 · 코드 32 · 코드 33 · 코드 34 · 코드 35
LMU	Permuted Accuracy 97.2%	Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks 2019-12-01	코드 1 · 코드 2
Adaptive-saturated RNN	Unpermuted Accuracy 99.3% Permuted Accuracy 96.96%	Adaptive-saturated RNN: Remember more with less instability 2023-04-24	코드 1
Sparse Combo Net	Permuted Accuracy 96.94	RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks 2021-06-16	코드 1
GAM-RHN-1	Permuted Accuracy 96.8%	Recurrent Highway Networks with Grouped Auxiliary Memory 2019-12-13	코드 1 · 코드 2 · 코드 3 · 코드 4
LEM	Unpermuted Accuracy 99.5% Permuted Accuracy 96.6%	Long Expressive Memory for Sequence Modeling 2021-10-10	코드 1
LipschitzRNN	Unpermuted Accuracy 99.4 Permuted Accuracy 96.3%	Lipschitz Recurrent Neural Networks 2020-06-22	코드 1
DNC+CUW	Unpermuted Accuracy 99.1% Permuted Accuracy 96.3%	Learning to Remember More with Less Memorization 2019-01-05	코드 1
IndRNN	Unpermuted Accuracy 99% Permuted Accuracy 96%	Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN 2018-03-13	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11
BN LSTM	Unpermuted Accuracy 99% Permuted Accuracy 95.4%	Recurrent Batch Normalization 2016-03-30	코드 1 · 코드 2 · 코드 3
EGRU	Unpermuted Accuracy 98.3% Permuted Accuracy 95.1%	Efficient recurrent architectures through activity sparsity and sparse back-propagation through time 2022-06-13	코드 1
Dilated GRU	Unpermuted Accuracy 99.2% Permuted Accuracy 94.6%	Dilated Recurrent Neural Networks 2017-10-05	코드 1 · 코드 2
Full-capacity uRNN	Unpermuted Accuracy 96.9% Permuted Accuracy 94.1%	Full-Capacity Unitary Recurrent Neural Networks 2016-10-31	코드 1 · 코드 2
LSTM	Unpermuted Accuracy 98.2% Permuted Accuracy 88%	Unitary Evolution Recurrent Neural Networks 2015-11-20	코드 1 · 코드 2
iRNN	Unpermuted Accuracy 97% Permuted Accuracy 82%	A Simple Way to Initialize Recurrent Networks of Rectified Linear Units 2015-04-03	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
FlexTCN-6	Unpermuted Accuracy 99.62%	FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes 2021-10-15	코드 1
STAR	Unpermuted Accuracy 99.4%	Gating Revisited: Deep Multi-layer RNNs That Can Be Trained 2019-11-25	코드 1 · 코드 2 · 코드 3
R-Transformer	Unpermuted Accuracy 99.1%	R-Transformer: Recurrent Neural Network Enhanced Transformer 2019-07-12	코드 1 · 코드 2