Sequential Image Classification On Sequential 1

Metrics

Unpermuted Accuracy

Results

Performance results of various models on this benchmark

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

0 of 13 row(s) selected.

Sequential Image Classification On Sequential 1

Metrics

Unpermuted Accuracy

Results

Performance results of various models on this benchmark

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

0 of 13 row(s) selected.

Sequential Image Classification On Sequential 1 | SOTA | HyperAI