{"task":"Sequential Image Classification","dataset":"Sequential MNIST","metric_names":["Permuted Accuracy","Unpermuted Accuracy"],"rows":[{"id":71963,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"SMPConv","metrics":{"Permuted Accuracy":"99.10","Unpermuted Accuracy":"99.75"},"paper_url":"https://arxiv.org/abs/2304.02330v1","paper_title":"SMPConv: Self-moving Point Representations for Continuous Convolution","paper_date":"2023-04-05","code_links":[{"title":"sangnekim/smpconv","url":"https://github.com/sangnekim/smpconv"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71964,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"LSSL","metrics":{"Permuted Accuracy":"98.76%","Unpermuted Accuracy":"99.53%"},"paper_url":"https://arxiv.org/abs/2110.13985v1","paper_title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","paper_date":"2021-10-26","code_links":[{"title":"hazyresearch/state-spaces","url":"https://github.com/hazyresearch/state-spaces"},{"title":"ag1988/dss","url":"https://github.com/ag1988/dss"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71965,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"FlexTCN-4","metrics":{"Permuted Accuracy":"98.72%"},"paper_url":"https://arxiv.org/abs/2110.08059v3","paper_title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","paper_date":"2021-10-15","code_links":[{"title":"rjbruin/flexconv","url":"https://github.com/rjbruin/flexconv"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71966,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"S4","metrics":{"Permuted Accuracy":"98.70%","Unpermuted Accuracy":"99.63%"},"paper_url":"https://arxiv.org/abs/2111.00396v3","paper_title":"Efficiently Modeling Long Sequences with Structured State Spaces","paper_date":"2021-10-31","code_links":[{"title":"state-spaces/s4","url":"https://github.com/state-spaces/s4"},{"title":"srush/annotated-s4","url":"https://github.com/srush/annotated-s4"},{"title":"ag1988/dss","url":"https://github.com/ag1988/dss"},{"title":"nicolaszucchet/minimal-lru","url":"https://github.com/nicolaszucchet/minimal-lru"},{"title":"forgi86/lru-reduction","url":"https://github.com/forgi86/lru-reduction"},{"title":"elgazzarr/fmri-s4","url":"https://github.com/elgazzarr/fmri-s4"},{"title":"maxtimer97/ssm-inspired-lif","url":"https://github.com/maxtimer97/ssm-inspired-lif"},{"title":"leonty1/essm","url":"https://github.com/leonty1/essm"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71967,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"CKCNN (1M)","metrics":{"Permuted Accuracy":"98.54%","Unpermuted Accuracy":"99.32%"},"paper_url":"https://arxiv.org/abs/2102.02611v3","paper_title":"CKConv: Continuous Kernel Convolution For Sequential Data","paper_date":"2021-02-04","code_links":[{"title":"dwromero/ckconv","url":"https://github.com/dwromero/ckconv"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71968,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Modified LMU (165k)","metrics":{"Permuted Accuracy":"98.49%"},"paper_url":"https://arxiv.org/abs/2102.11417v2","paper_title":"Parallelizing Legendre Memory Unit Training","paper_date":"2021-02-22","code_links":[{"title":"hrshtv/pytorch-lmu","url":"https://github.com/hrshtv/pytorch-lmu"},{"title":"elisejiuqizhang/jax-lmu","url":"https://github.com/elisejiuqizhang/jax-lmu"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71969,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"UnICORNN","metrics":{"Permuted Accuracy":"98.4"},"paper_url":"https://arxiv.org/abs/2103.05487v2","paper_title":"UnICORNN: A recurrent model for learning very long time dependencies","paper_date":"2021-03-09","code_links":[{"title":"tk-rusch/unicornn","url":"https://github.com/tk-rusch/unicornn"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71970,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"HiPPO-LegS","metrics":{"Permuted Accuracy":"98.3%"},"paper_url":"https://arxiv.org/abs/2008.07669v2","paper_title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","paper_date":"2020-08-17","code_links":[{"title":"HazyResearch/hippo-code","url":"https://github.com/HazyResearch/hippo-code"},{"title":"ag1988/dss","url":"https://github.com/ag1988/dss"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71971,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"CKCNN (100k)","metrics":{"Permuted Accuracy":"98%","Unpermuted Accuracy":"99.31%"},"paper_url":"https://arxiv.org/abs/2102.02611v3","paper_title":"CKConv: Continuous Kernel Convolution For Sequential Data","paper_date":"2021-02-04","code_links":[{"title":"dwromero/ckconv","url":"https://github.com/dwromero/ckconv"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71972,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"ODE-LSTM","metrics":{"Permuted Accuracy":"97.83%"},"paper_url":"https://arxiv.org/abs/2006.04418v4","paper_title":"Learning Long-Term Dependencies in Irregularly-Sampled Time Series","paper_date":"2020-06-08","code_links":[{"title":"mlech26l/learning-long-term-irregular-ts","url":"https://github.com/mlech26l/learning-long-term-irregular-ts"},{"title":"mlech26l/ode-lstms","url":"https://github.com/mlech26l/ode-lstms"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71973,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"coRNN","metrics":{"Permuted Accuracy":"97.34%","Unpermuted Accuracy":"99.4%"},"paper_url":"https://arxiv.org/abs/2010.00951v2","paper_title":"Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies","paper_date":"2020-10-02","code_links":[{"title":"tk-rusch/coRNN","url":"https://github.com/tk-rusch/coRNN"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71974,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Dense IndRNN","metrics":{"Permuted Accuracy":"97.2%","Unpermuted Accuracy":"99.48%"},"paper_url":"https://arxiv.org/abs/1910.06251v3","paper_title":"Deep Independently Recurrent Neural Network (IndRNN)","paper_date":"2019-10-11","code_links":[{"title":"Sunnydreamrain/IndRNN_pytorch","url":"https://github.com/Sunnydreamrain/IndRNN_pytorch"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71975,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Temporal Convolutional Network","metrics":{"Permuted Accuracy":"97.2%","Unpermuted Accuracy":"99.0%"},"paper_url":"http://arxiv.org/abs/1803.01271v2","paper_title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","paper_date":"2018-03-04","code_links":[{"title":"timeseriesAI/tsai","url":"https://github.com/timeseriesAI/tsai/tree/main/tsai/models"},{"title":"locuslab/TCN","url":"https://github.com/locuslab/TCN"},{"title":"philipperemy/keras-tcn","url":"https://github.com/philipperemy/keras-tcn"},{"title":"WenjieDu/PyPOTS","url":"https://github.com/WenjieDu/PyPOTS"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/TCN"},{"title":"proroklab/popgym","url":"https://github.com/proroklab/popgym"},{"title":"mhjabreel/CharCnn_Keras","url":"https://github.com/mhjabreel/CharCnn_Keras"},{"title":"Baichenjia/Tensorflow-TCN","url":"https://github.com/Baichenjia/Tensorflow-TCN"},{"title":"Songweiping/TCN-TF","url":"https://github.com/Songweiping/TCN-TF"},{"title":"YuanTingHsieh/TF_TCN","url":"https://github.com/YuanTingHsieh/TF_TCN"},{"title":"sindhura97/STraTS","url":"https://github.com/sindhura97/STraTS"},{"title":"rvandewater/yaib","url":"https://github.com/rvandewater/yaib"},{"title":"ashishpatel26/tcn-keras-Examples","url":"https://github.com/ashishpatel26/tcn-keras-Examples"},{"title":"ratschlab/HIRID-ICU-Benchmark","url":"https://github.com/ratschlab/HIRID-ICU-Benchmark"},{"title":"jakeret/tcn","url":"https://github.com/jakeret/tcn"},{"title":"zhong110020/pytorch_TCN","url":"https://github.com/zhong110020/pytorch_TCN"},{"title":"XiaowanLi2018/TimeSeriesPrediction_BasedOnCNN","url":"https://github.com/XiaowanLi2018/TimeSeriesPrediction_BasedOnCNN"},{"title":"tw-yuhsi/a-new-perspective-for-shuttlecock-hitting-event-detection","url":"https://github.com/tw-yuhsi/a-new-perspective-for-shuttlecock-hitting-event-detection"},{"title":"wish44165/A-New-Perspective-for-Shuttlecock-Hitting-Event-Detection","url":"https://github.com/wish44165/A-New-Perspective-for-Shuttlecock-Hitting-Event-Detection"},{"title":"zhong110020/keras-tcn","url":"https://github.com/zhong110020/keras-tcn"},{"title":"jxz542189/TCN_classification","url":"https://github.com/jxz542189/TCN_classification"},{"title":"selmiss/gp-tlstgcn","url":"https://github.com/selmiss/gp-tlstgcn"},{"title":"anandharaju/Basic_TCN","url":"https://github.com/anandharaju/Basic_TCN"},{"title":"ShotDownDiane/tcn-master","url":"https://github.com/ShotDownDiane/tcn-master"},{"title":"patHutchings/TCN","url":"https://github.com/patHutchings/TCN"},{"title":"ZTianle/keras-tcn-solar","url":"https://github.com/ZTianle/keras-tcn-solar"},{"title":"MChen9/TCN","url":"https://github.com/MChen9/TCN"},{"title":"zll1996/TCN","url":"https://github.com/zll1996/TCN"},{"title":"zhong110020/Tensorflow-TCN","url":"https://github.com/zhong110020/Tensorflow-TCN"},{"title":"Nic5472K/FriendsOOGroup_TCN","url":"https://github.com/Nic5472K/FriendsOOGroup_TCN"},{"title":"kingcong/TCN","url":"https://github.com/kingcong/TCN"},{"title":"zhong110020/TensorFlow_TCN","url":"https://github.com/zhong110020/TensorFlow_TCN"},{"title":"sucheta19/Text-Classification-Using-CNN","url":"https://github.com/sucheta19/Text-Classification-Using-CNN"},{"title":"hkchengrex/TCN","url":"https://github.com/hkchengrex/TCN"},{"title":"linxi159/TCN","url":"https://github.com/linxi159/TCN"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71976,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"LMU","metrics":{"Permuted Accuracy":"97.2%"},"paper_url":"http://papers.nips.cc/paper/9689-legendre-memory-units-continuous-time-representation-in-recurrent-neural-networks","paper_title":"Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks","paper_date":"2019-12-01","code_links":[{"title":"abr/neurips2019","url":"https://github.com/abr/neurips2019"},{"title":"hrshtv/pytorch-lmu","url":"https://github.com/hrshtv/pytorch-lmu"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71977,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Adaptive-saturated RNN","metrics":{"Permuted Accuracy":"96.96%","Unpermuted Accuracy":"99.3%"},"paper_url":"https://arxiv.org/abs/2304.11790v1","paper_title":"Adaptive-saturated RNN: Remember more with less instability","paper_date":"2023-04-24","code_links":[{"title":"ndminhkhoi46/asRNN","url":"https://github.com/ndminhkhoi46/asRNN"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71978,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Sparse Combo Net","metrics":{"Permuted Accuracy":"96.94"},"paper_url":"https://arxiv.org/abs/2106.08928v6","paper_title":"RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks","paper_date":"2021-06-16","code_links":[{"title":"ennisthemennis/sparse-combo-net","url":"https://github.com/ennisthemennis/sparse-combo-net"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71979,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"GAM-RHN-1","metrics":{"Permuted Accuracy":"96.8%"},"paper_url":"https://ieeexplore.ieee.org/document/8932404","paper_title":"Recurrent Highway Networks with Grouped Auxiliary Memory","paper_date":"2019-12-13","code_links":[{"title":"WilliamRo/gam_rhn","url":"https://github.com/WilliamRo/gam_rhn"},{"title":"MindCode-4/code-8","url":"https://github.com/MindCode-4/code-8/tree/main/recurrent-highway-network"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/recurrent-highway-network"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/recurrent-highway-network"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71980,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"LEM","metrics":{"Permuted Accuracy":"96.6%","Unpermuted Accuracy":"99.5%"},"paper_url":"https://arxiv.org/abs/2110.04744v2","paper_title":"Long Expressive Memory for Sequence Modeling","paper_date":"2021-10-10","code_links":[{"title":"tk-rusch/lem","url":"https://github.com/tk-rusch/lem"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71981,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"LipschitzRNN","metrics":{"Permuted Accuracy":"96.3%","Unpermuted Accuracy":"99.4"},"paper_url":"https://arxiv.org/abs/2006.12070v3","paper_title":"Lipschitz Recurrent Neural Networks","paper_date":"2020-06-22","code_links":[{"title":"erichson/LipschitzRNN","url":"https://github.com/erichson/LipschitzRNN"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71982,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"DNC+CUW","metrics":{"Permuted Accuracy":"96.3%","Unpermuted Accuracy":"99.1%"},"paper_url":"http://arxiv.org/abs/1901.01347v2","paper_title":"Learning to Remember More with Less Memorization","paper_date":"2019-01-05","code_links":[{"title":"thaihungle/UW-DNC","url":"https://github.com/thaihungle/UW-DNC"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71983,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"IndRNN","metrics":{"Permuted Accuracy":"96%","Unpermuted Accuracy":"99%"},"paper_url":"http://arxiv.org/abs/1803.04831v3","paper_title":"Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN","paper_date":"2018-03-13","code_links":[{"title":"TobiasLee/Text-Classification","url":"https://github.com/TobiasLee/Text-Classification"},{"title":"batzner/indrnn","url":"https://github.com/batzner/indrnn"},{"title":"lmnt-com/haste","url":"https://github.com/lmnt-com/haste"},{"title":"Sunnydreamrain/IndRNN_pytorch","url":"https://github.com/Sunnydreamrain/IndRNN_pytorch"},{"title":"StefOe/indrnn-pytorch","url":"https://github.com/StefOe/indrnn-pytorch"},{"title":"Sunnydreamrain/IndRNN_Theano_Lasagne","url":"https://github.com/Sunnydreamrain/IndRNN_Theano_Lasagne"},{"title":"amcs1729/Predicting-cloud-CPU-usage-on-Azure-data","url":"https://github.com/amcs1729/Predicting-cloud-CPU-usage-on-Azure-data"},{"title":"trevor-richardson/rnn_zoo","url":"https://github.com/trevor-richardson/rnn_zoo"},{"title":"secretlyvogon/IndRNNTF","url":"https://github.com/secretlyvogon/IndRNNTF"},{"title":"secretlyvogon/Neural-Network-Implementations","url":"https://github.com/secretlyvogon/Neural-Network-Implementations"},{"title":"Sunnydreamrain/IndRNN","url":"https://github.com/Sunnydreamrain/IndRNN"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71984,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"BN LSTM","metrics":{"Permuted Accuracy":"95.4%","Unpermuted Accuracy":"99%"},"paper_url":"http://arxiv.org/abs/1603.09025v5","paper_title":"Recurrent Batch Normalization","paper_date":"2016-03-30","code_links":[{"title":"cooijmanstim/recurrent-batch-normalization","url":"https://github.com/cooijmanstim/recurrent-batch-normalization"},{"title":"codedecde/Recognizing-Textual-Entailment","url":"https://github.com/codedecde/Recognizing-Textual-Entailment"},{"title":"Tetsuya-Nishikawa/ConvLSTM_DEMO","url":"https://github.com/Tetsuya-Nishikawa/ConvLSTM_DEMO"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71985,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"EGRU","metrics":{"Permuted Accuracy":"95.1%","Unpermuted Accuracy":"98.3%"},"paper_url":"https://arxiv.org/abs/2206.06178v3","paper_title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","paper_date":"2022-06-13","code_links":[{"title":"khaleelkhan/evnn","url":"https://github.com/khaleelkhan/evnn"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71986,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Dilated GRU","metrics":{"Permuted Accuracy":"94.6%","Unpermuted Accuracy":"99.2%"},"paper_url":"http://arxiv.org/abs/1710.02224v3","paper_title":"Dilated Recurrent Neural Networks","paper_date":"2017-10-05","code_links":[{"title":"code-terminator/DilatedRNN","url":"https://github.com/code-terminator/DilatedRNN"},{"title":"zalandoresearch/pytorch-dilated-rnn","url":"https://github.com/zalandoresearch/pytorch-dilated-rnn"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71987,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"Full-capacity uRNN","metrics":{"Permuted Accuracy":"94.1%","Unpermuted Accuracy":"96.9%"},"paper_url":"http://arxiv.org/abs/1611.00035v1","paper_title":"Full-Capacity Unitary Recurrent Neural Networks","paper_date":"2016-10-31","code_links":[{"title":"stwisdom/urnn","url":"https://github.com/stwisdom/urnn"},{"title":"v0lta/Complex-gated-recurrent-neural-networks","url":"https://github.com/v0lta/Complex-gated-recurrent-neural-networks"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71988,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"LSTM","metrics":{"Permuted Accuracy":"88%","Unpermuted Accuracy":"98.2%"},"paper_url":"http://arxiv.org/abs/1511.06464v4","paper_title":"Unitary Evolution Recurrent Neural Networks","paper_date":"2015-11-20","code_links":[{"title":"v0lta/Complex-gated-recurrent-neural-networks","url":"https://github.com/v0lta/Complex-gated-recurrent-neural-networks"},{"title":"rand0musername/urnn","url":"https://github.com/rand0musername/urnn"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71989,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"iRNN","metrics":{"Permuted Accuracy":"82%","Unpermuted Accuracy":"97%"},"paper_url":"http://arxiv.org/abs/1504.00941v2","paper_title":"A Simple Way to Initialize Recurrent Networks of Rectified Linear Units","paper_date":"2015-04-03","code_links":[{"title":"facebookresearch/salina","url":"https://github.com/facebookresearch/salina"},{"title":"sobhan-moosavi/characterizingdrivingstyleswithdeeplearning","url":"https://github.com/sobhan-moosavi/characterizingdrivingstyleswithdeeplearning"},{"title":"mindspore-courses/DeepNLP-models-MindSpore","url":"https://github.com/mindspore-courses/DeepNLP-models-MindSpore"},{"title":"trevor-richardson/rnn_zoo","url":"https://github.com/trevor-richardson/rnn_zoo"},{"title":"adamx97/Data-Science-Advanced-Capstone","url":"https://github.com/adamx97/Data-Science-Advanced-Capstone"},{"title":"minhtriet/gridworld","url":"https://github.com/minhtriet/gridworld"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71990,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"FlexTCN-6","metrics":{"Unpermuted Accuracy":"99.62%"},"paper_url":"https://arxiv.org/abs/2110.08059v3","paper_title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","paper_date":"2021-10-15","code_links":[{"title":"rjbruin/flexconv","url":"https://github.com/rjbruin/flexconv"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71991,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"STAR","metrics":{"Unpermuted Accuracy":"99.4%"},"paper_url":"https://arxiv.org/abs/1911.11033v4","paper_title":"Gating Revisited: Deep Multi-layer RNNs That Can Be Trained","paper_date":"2019-11-25","code_links":[{"title":"0zgur0/STAR_Network","url":"https://github.com/0zgur0/STAR_Network"},{"title":"titu1994/tf_star_rnn","url":"https://github.com/titu1994/tf_star_rnn"},{"title":"croros/STAR_Network_Pytorch","url":"https://github.com/croros/STAR_Network_Pytorch"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":71992,"task":"Sequential Image Classification","parent_task":"Image Classification","dataset":"Sequential MNIST","model_name":"R-Transformer","metrics":{"Unpermuted Accuracy":"99.1%"},"paper_url":"https://arxiv.org/abs/1907.05572v1","paper_title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","paper_date":"2019-07-12","code_links":[{"title":"DSE-MSU/R-transformer","url":"https://github.com/DSE-MSU/R-transformer"},{"title":"sfox14/butterfly-r-transformer","url":"https://github.com/sfox14/butterfly-r-transformer"}],"metrics_order":"[\"Permuted Accuracy\", \"Unpermuted Accuracy\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]}]}